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

    Neuronpedia

    INDEX
    Explanations

    instances of reporting, particularly the verb "told."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sauvages
    -0.61
     secondly
    -0.61
     marquées
    -0.60
    RUnlock
    -0.59
    cuerdo
    -0.56
     Baillargeon
    -0.53
     Secondly
    -0.53
     otomatig
    -0.52
     päivä
    -0.51
     dividido
    -0.51
    POSITIVE LOGITS
    ########.
    0.71
     reporters
    0.66
    SocketChannel
    0.61
    ymal
    0.59
    rawDesc
    0.56
    HttpFoundation
    0.56
    EMBLY
    0.56
    endsection
    0.55
    __':
    0.55
    enterOuterAlt
    0.54
    Act Density 0.083%

    No Known Activations