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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a statement or opinion being expressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions involving the word "say" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ells
    -0.67
    pes
    -0.66
    figure
    -0.66
    imeo
    -0.65
    emort
    -0.65
    ancies
    -0.65
    catentry
    -0.61
     obser
    -0.60
    ilan
    -0.60
    etimes
    -0.60
    POSITIVE LOGITS
     that
    1.23
     otherwise
    0.91
     goodbye
    0.90
    that
    0.89
     THAT
    0.85
     thats
    0.77
     we
    0.76
     they
    0.71
     there
    0.70
     unequivocally
    0.69
    Act Density 0.144%

    No Known Activations