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

    Neuronpedia

    INDEX
    Explanations

    references to elephants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of elephants and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.93
    nder
    -0.87
    nergy
    -0.83
    ndra
    -0.81
    lly
    -0.81
    lished
    -0.78
    nda
    -0.78
    nces
    -0.76
    ername
    -0.76
    nerg
    -0.75
    POSITIVE LOGITS
     elephant
    1.19
     elephants
    1.15
    iasis
    1.15
     herds
    0.93
     Elephant
    0.91
     ivory
    0.89
     poaching
    0.87
     calf
    0.87
     Haram
    0.86
    monary
    0.84
    Act Density 0.024%

    No Known Activations