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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and conditional phrases that indicate relationships or dependencies between statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [*]
    -0.59
     FetchType
    -0.56
    出版年
    -0.56
     onCreateView
    -0.56
    WebVitals
    -0.56
     textStatus
    -0.53
     savent
    -0.52
    fileupload
    -0.51
    -0.50
     surla
    -0.50
    POSITIVE LOGITS
    rogens
    0.68
    MarshalTo
    0.51
     TextAppearance
    0.50
    RTEX
    0.49
    
    0.48
    ksessa
    0.46
    зня
    0.46
    ginal
    0.45
    TAIN
    0.45
    Inggris
    0.45
    Act Density 0.286%

    No Known Activations