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

    Neuronpedia

    INDEX
    Explanations

    clauses starting with a verb and followed by a comma

    oai_token-act-pair · gpt-3.5-turbo

    punctuations or pauses that separate ideas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAX
    -0.68
    osc
    -0.62
    nih
    -0.58
    ANN
    -0.58
    rand
    -0.56
    untarily
    -0.56
    num
    -0.55
    ocalypse
    -0.55
    TY
    -0.55
    phant
    -0.54
    POSITIVE LOGITS
     meanwhile
    1.41
     however
    1.30
     huh
    1.08
     moreover
    1.02
     alas
    0.93
     unsurprisingly
    0.93
     therefore
    0.90
     albeit
    0.86
     namely
    0.82
     though
    0.81
    Act Density 0.414%

    No Known Activations