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

    Neuronpedia

    INDEX
    Explanations

    names or entities with 'je' in them

    oai_token-act-pair · gpt-3.5-turbo

    names, specifically proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.83
    moving
    -0.75
    prop
    -0.74
    iqu
    -0.73
    norm
    -0.70
    izoph
    -0.70
    ãĥ£
    -0.69
    iques
    -0.68
    markets
    -0.68
    runner
    -0.66
    POSITIVE LOGITS
    lde
    1.08
    anwhile
    1.03
    lda
    0.87
    llan
    0.86
    gger
    0.84
    cki
    0.80
    ktop
    0.78
    ansen
    0.78
    chal
    0.77
    irs
    0.77
    Act Density 0.037%

    No Known Activations