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

    Neuronpedia

    INDEX
    Explanations

    statements that express opinions, claims, or factual assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tal
    -0.64
    B
    -0.59
    the
    -0.58
    so
    -0.58
    式
    -0.56
    sof
    -0.56
    son
    -0.56
    sp
    -0.56
    turn
    -0.54
    ton
    -0.54
    POSITIVE LOGITS
    ')")
    0.95
     itſelf
    0.87
     كومونز
    0.87
    encils
    0.87
    '%(
    0.83
    namefont
    0.82
     дописавши
    0.82
    Jaunes
    0.82
     ")[
    0.81
    ingtones
    0.81
    Act Density 0.569%

    No Known Activations