Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to accepting or welcoming new ideas, changes, or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "embrace" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.71
    cano
    -0.70
    akov
    -0.70
    etry
    -0.66
    opers
    -0.65
    selves
    -0.65
    arcity
    -0.63
    gm
    -0.63
    acca
    -0.62
     tatt
    -0.62
    POSITIVE LOGITS
     embrace
    0.76
     embraces
    0.74
    aneers
    0.71
    edIn
    0.68
    glers
    0.68
    tails
    0.67
    VILLE
    0.66
     diversity
    0.65
    prise
    0.64
     uncond
    0.63
    Act Density 0.029%

    No Known Activations