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

    Neuronpedia

    INDEX
    Explanations

    discussions about quantities and events involving groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !
    -0.71
     segala
    -0.56
    :
    -0.56
    lec
    -0.54
     ‘
    -0.53
    l
    -0.52
    まさかの
    -0.50
    !”
    -0.49
    ついに
    -0.48
    ml
    -0.48
    POSITIVE LOGITS
    antaine
    1.14
     typelib
    1.06
    SourceChecksum
    1.00
    MLLoader
    1.00
    enumii
    1.00
    complexContent
    0.94
    ########.
    0.93
     estekak
    0.90
     HasFactory
    0.89
    MethodManager
    0.88
    Act Density 0.373%

    No Known Activations