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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lace
    -0.17
     Pur
    -0.17
    ighton
    -0.17
    er
    -0.16
     иÑģÑĤ
    -0.16
    als
    -0.15
    thing
    -0.15
    ForResult
    -0.14
    ÑĸÑĤи
    -0.14
     Kết
    -0.14
    POSITIVE LOGITS
    antly
    0.33
    물ìĿĦ
    0.23
    물
    0.19
    ingly
    0.19
    ants
    0.18
    ados
    0.18
    oure
    0.17
    antz
    0.17
    ntag
    0.17
    ively
    0.16
    Act Density 0.057%

    No Known Activations