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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itudinal
    -0.68
     Hemisphere
    -0.68
    inally
    -0.67
    matically
    -0.65
    boards
    -0.64
     ultras
    -0.63
     metic
    -0.62
     Else
    -0.62
     Colombian
    -0.61
     brightest
    -0.61
    POSITIVE LOGITS
    ttes
    1.00
    lette
    0.84
    otte
    0.82
    borg
    0.79
    ecake
    0.78
    lected
    0.77
    zza
    0.77
    qv
    0.77
    lection
    0.74
    erest
    0.73
    Act Density 0.018%

    No Known Activations