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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs and words indicating obligation or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Į¨
    -0.14
    toMatch
    -0.13
    iglia
    -0.12
    εια
    -0.12
    PÅĻed
    -0.12
    िà¤ķल
    -0.12
    ojÃŃ
    -0.11
    aucoup
    -0.11
    inspace
    -0.11
    posables
    -0.11
    POSITIVE LOGITS
     not
    1.34
    not
    1.09
     NOT
    1.05
     Not
    0.98
    Not
    0.90
    _not
    0.84
    -not
    0.84
    .not
    0.83
    	not
    0.79
    NOT
    0.77
    Act Density 1.082%

    No Known Activations