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

    Neuronpedia

    INDEX
    Explanations

    references to gaining knowledge or information

    oai_token-act-pair · gpt-3.5-turbo

    the word "you" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ice
    -0.78
    math
    -0.71
     Chap
    -0.66
     Canaver
    -0.65
    ipal
    -0.64
    images
    -0.64
     Gibbs
    -0.62
    icy
    -0.61
    hover
    -0.60
     Arkham
    -0.58
    POSITIVE LOGITS
    're
    1.32
    've
    1.19
    'll
    1.12
     guys
    1.10
    tub
    1.08
    'd
    0.97
    RS
    0.93
     yourselves
    0.93
     want
    0.90
     wanna
    0.90
    Act Density 0.099%

    No Known Activations