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

    Neuronpedia

    INDEX
    Explanations

    short interrogative sentences

    oai_token-act-pair · gpt-3.5-turbo

    questions and reflections on past events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.69
     conduc
    -0.66
    ebted
    -0.65
    artifacts
    -0.60
     redes
    -0.60
     Contains
    -0.60
    yright
    -0.59
    emale
    -0.58
    ģĸ
    -0.57
    Located
    -0.56
    POSITIVE LOGITS
     he
    1.23
     I
    0.95
     everybody
    0.95
     we
    0.93
     she
    0.93
     somebody
    0.92
     they
    0.92
     you
    0.89
     [
    0.86
     anybody
    0.86
    Act Density 0.382%

    No Known Activations