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

    Neuronpedia

    INDEX
    Explanations

    textual code structures and formatting patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pole
    -0.15
     Frem
    -0.14
    anner
    -0.14
     manner
    -0.14
     nhau
    -0.14
    oce
    -0.14
    gi
    -0.14
    _UNUSED
    -0.14
    stown
    -0.14
     Hut
    -0.14
    POSITIVE LOGITS
    itzer
    0.15
    teg
    0.15
     sho
    0.14
    bson
    0.14
    zano
    0.14
    Bindable
    0.14
    askan
    0.14
    @qq
    0.13
     INTERRUPTION
    0.13
    gst
    0.13
    Act Density 0.010%

    No Known Activations