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

    Neuronpedia

    INDEX
    Explanations

    quoted text and punctuation-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     super
    -0.40
     Cuban
    -0.39
     hard
    -0.38
    }{|
    -0.37
    ModelSerializer
    -0.36
     red
    -0.36
     du
    -0.36
    iliares
    -0.35
     rest
    -0.34
    Cls
    -0.34
    POSITIVE LOGITS
     مشين
    0.68
    RTHOOK
    0.66
    writeField
    0.62
    featureID
    0.57
    Tikang
    0.56
     autorytatywna
    0.56
    ftagPool
    0.56
     незавершена
    0.56
    ’”
    0.53
    stylers
    0.53
    Act Density 0.323%

    No Known Activations