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

    Neuronpedia

    INDEX
    Explanations

    questions and conditional phrases throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.84
    UnusedPrivate
    -0.77
    AutoScaleMode
    -0.66
    tagHelperRunner
    -0.61
     "..\..\
    -0.58
     كومونز
    -0.58
     betweenstory
    -0.57
    IsMutable
    -0.55
    GIVEREF
    -0.55
     PyLong
    -0.54
    POSITIVE LOGITS
    why
    0.99
     why
    0.97
    where
    0.91
     cuándo
    0.87
    Where
    0.87
    Why
    0.84
     wherefore
    0.83
     Where
    0.83
     Why
    0.83
    how
    0.82
    Act Density 0.175%

    No Known Activations