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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating potential situations or actions

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

    "If" followed by a conditional statement

    np_acts-logits-general · gemini-2.0-flash

    if you or your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.79
     HasFactory
    -0.78
    /**
    -0.68
     ويكيميديا
    -0.68
    MigrationBuilder
    -0.67
    InitVars
    -0.66
    complexContent
    -0.66
     actionTypes
    -0.65
     henvisninger
    -0.63
     gynhyrchwyd
    -0.63
    POSITIVE LOGITS
     necessary
    0.76
     unable
    0.68
     nodig
    0.65
     necesario
    0.58
     doubtful
    0.56
     still
    0.56
     dúvida
    0.54
     If
    0.53
     nødven
    0.53
     demikian
    0.52
    Act Density 0.188%

    No Known Activations