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

    Neuronpedia

    INDEX
    Explanations

    interrogative structures and responses related to personal opinions and preferences

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

    Word before "and"

    np_acts-logits-general · gemini-2.0-flash

    asking someone what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sin
    -0.49
     [
    -0.46
    ↵↵
    -0.45
     E
    -0.45
     Man
    -0.44
     O
    -0.43
     (
    -0.43
    app
    -0.42
     through
    -0.42
     N
    -0.42
    POSITIVE LOGITS
     HasFactory
    0.92
     jadx
    0.84
    \{\\
    0.80
    '},
    0.76
     Anſ
    0.76
     NSCoder
    0.75
     adjectives
    0.75
     Efq
    0.73
     ―――――
    0.72
    aday
    0.71
    Act Density 0.180%

    No Known Activations