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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that a specific event or action is scheduled to occur

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating scheduled events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.94
    asive
    -0.66
    inventoryQuantity
    -0.63
    isks
    -0.63
    paste
    -0.61
    ãģķ
    -0.60
     medial
    -0.59
    udeau
    -0.59
    ilee
    -0.58
     Taste
    -0.58
    POSITIVE LOGITS
    tle
    1.04
     abl
    0.86
    offs
    0.85
    tering
    0.84
    list
    0.82
    ters
    0.81
    itud
    0.79
     forth
    0.77
    tered
    0.77
    lists
    0.77
    Act Density 0.036%

    No Known Activations