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

    Neuronpedia

    INDEX
    Explanations

    phrases that express doubt or challenge conventional beliefs

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

    questioning and doubting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fix
    -0.31
    AutoScaleMode
    -0.30
     Vergnügen
    -0.30
     promociones
    -0.29
     hän
    -0.28
     hoffe
    -0.28
     fenómeno
    -0.27
     protectora
    -0.27
     nélk
    -0.27
    fix
    -0.26
    POSITIVE LOGITS
     questioning
    0.88
     questioned
    0.86
     cuestion
    0.85
     doubting
    0.82
    Chall
    0.77
    challenged
    0.77
     Challenging
    0.76
     Chall
    0.74
    质疑
    0.74
     challenged
    0.72
    Act Density 0.164%

    No Known Activations