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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong emotions or assertive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    гра
    -0.47
    inkan
    -0.47
     Boy
    -0.45
     character
    -0.45
    午後
    -0.44
    Attrs
    -0.44
    Fac
    -0.44
     Jed
    -0.43
    ilak
    -0.42
    werb
    -0.42
    POSITIVE LOGITS
    ########.
    0.88
    tagext
    0.83
     typelib
    0.82
    SharedDtor
    0.81
    IContainer
    0.77
     @"/
    0.76
    bootstrapcdn
    0.76
    IntoConstraints
    0.75
    ValueStyle
    0.74
     ब्रेकडाउन
    0.73
    Act Density 0.154%

    No Known Activations