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

    Neuronpedia

    INDEX
    Explanations

    language related to shaping or altering objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouch
    -0.16
     Leigh
    -0.15
    ngrx
    -0.14
    peace
    -0.14
    ean
    -0.14
    OUCH
    -0.14
    isle
    -0.13
     æĻ´
    -0.13
    orks
    -0.13
    æĮ¯ãĤĬ
    -0.13
    POSITIVE LOGITS
    æĬĺ
    0.16
    kest
    0.15
    angen
    0.14
    Restricted
    0.14
    бов
    0.14
     Hos
    0.14
     veter
    0.14
    explo
    0.14
    ovo
    0.13
    IVES
    0.13
    Act Density 0.018%

    No Known Activations