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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "throw" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    datal
    -0.17
    ialized
    -0.16
    tfoot
    -0.16
    ummings
    -0.15
     Dalton
    -0.15
    Ñıг
    -0.15
    ello
    -0.15
    _OVERRIDE
    -0.15
    ifo
    -0.15
    ial
    -0.15
    POSITIVE LOGITS
    back
    0.18
    away
    0.17
    ichen
    0.17
    ES
    0.16
    iminal
    0.15
    igh
    0.15
    a
    0.15
    ion
    0.14
    itz
    0.14
    Instantiate
    0.14
    Act Density 0.020%

    No Known Activations