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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries about motivations and reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Why" followed by a question

    np_acts-logits-general · gemini-2.0-flash

    questions asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.69
     otomatig
    -0.56
    MigrationBuilder
    -0.53
    fillType
    -0.52
    localctx
    -0.50
     Chwiliwch
    -0.50
     beginnetje
    -0.48
     Roskov
    -0.45
    stdc
    -0.44
     ligiloj
    -0.43
    POSITIVE LOGITS
    AutoField
    0.39
    ToAction
    0.36
     &___
    0.36
     ESPECIAL
    0.35
    ikki
    0.32
    TacToe
    0.32
    Alors
    0.31
    ariato
    0.31
     specialists
    0.31
     emulsi
    0.31
    Act Density 0.575%

    No Known Activations