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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters indicating numerical values or items in lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oplasmic
    -0.52
    lück
    -0.51
    बस
    -0.51
    liminary
    -0.50
     solace
    -0.50
    HTH
    -0.50
    getitem
    -0.49
    volent
    -0.49
    noscript
    -0.49
    veno
    -0.49
    POSITIVE LOGITS
    MemoryWarning
    0.69
    ScopeManager
    0.69
     useAuth
    0.67
    enderror
    0.67
    таратура
    0.64
     مرئيه
    0.62
    Vidite
    0.59
    modelBuilder
    0.58
     mû
    0.56
    isContained
    0.55
    Act Density 0.516%

    No Known Activations