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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating self-identity and personal state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     podjela
    -0.42
    󠁴
    -0.39
    AndEndTag
    -0.38
    ً
    -0.36
     swore
    -0.36
    还想
    -0.35
     hayas
    -0.33
     éta
    -0.33
     enough
    -0.33
     marqué
    -0.33
    POSITIVE LOGITS
    uxxxx
    0.69
    EndInit
    0.66
    mektedir
    0.60
    rungsseite
    0.59
     ExecuteAsync
    0.55
    miştir
    0.53
     입니다
    0.53
     medesimo
    0.52
     désolés
    0.52
    DataContract
    0.50
    Act Density 0.442%

    No Known Activations