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

    Neuronpedia

    INDEX
    Explanations

    modal verbs associated with future actions or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -1.09
    parsedMessage
    -0.88
    Composable
    -0.83
     CURIAM
    -0.83
     Jefus
    -0.81
     Chrift
    -0.79
    opsida
    -0.79
     Chriftian
    -0.77
     cellspacing
    -0.76
     newData
    -0.75
    POSITIVE LOGITS
     be
    1.22
     will
    1.21
     WILL
    1.20
     Will
    1.16
     likely
    0.99
    WILL
    0.99
    Will
    0.97
    will
    0.95
     surely
    0.91
     eventually
    0.83
    Act Density 0.184%

    No Known Activations