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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cell"

    oai_token-act-pair · gpt-3.5-turbo

    references to cellular structures or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.77
    ammy
    -0.75
    lift
    -0.74
    giving
    -0.73
    laus
    -0.72
    Keefe
    -0.70
    gettable
    -0.69
    raint
    -0.69
     cumbers
    -0.68
    reality
    -0.67
    POSITIVE LOGITS
    ular
    1.16
    estial
    0.90
    ades
    0.81
    iac
    0.81
    ency
    0.80
    ularity
    0.80
    otte
    0.79
    ade
    0.79
    oths
    0.78
    arette
    0.77
    Act Density 0.012%

    No Known Activations