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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and certain structural elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discorso
    -0.63
     newBuilder
    -0.63
    AsUp
    -0.60
     Numerade
    -0.59
     ú
    -0.56
     linkovi
    -0.55
     mostrarán
    -0.55
     préférence
    -0.53
     Aggi
    -0.53
     compito
    -0.52
    POSITIVE LOGITS
    󠁿
    0.75
     виправивши
    0.70
    ValueStyle
    0.67
    ScopeManager
    0.59
     Waray
    0.58
     BorderRadius
    0.56
    CloseOperation
    0.55
    <bos>
    0.55
    ">“
    0.54
    //
    0.54
    Act Density 0.061%

    No Known Activations