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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fact."

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

    in fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.32
    simpleType
    -0.32
    +?
    -0.32
    又是
    -0.31
    又要
    -0.31
    enderror
    -0.31
    折
    -0.31
     carrier
    -0.28
     climat
    -0.28
    =?,
    -0.28
    POSITIVE LOGITS
     anzi
    0.82
     infatti
    0.73
    ailleurs
    0.70
    Bahkan
    0.69
     Bahkan
    0.68
     faktisk
    0.68
    事实上
    0.67
     Gegenteil
    0.66
     linkovi
    0.66
     fact
    0.65
    Act Density 0.100%

    No Known Activations