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

    Neuronpedia

    INDEX
    Explanations

    references to actions related to playing or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.20
     someone
    -0.18
     Someone
    -0.17
    ĻĤ
    -0.17
     somebody
    -0.16
    htar
    -0.16
    ä¸Ģ个人
    -0.15
     alguien
    -0.15
    odd
    -0.14
    Someone
    -0.14
    POSITIVE LOGITS
     quite
    0.36
     such
    0.33
    quite
    0.27
     Quite
    0.26
     SUCH
    0.26
     somewhat
    0.24
    such
    0.22
    Such
    0.20
     Such
    0.20
     kind
    0.17
    Act Density 0.156%

    No Known Activations