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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and expressions of intention or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëģĶ
    -0.15
     swear
    -0.14
    ocab
    -0.14
    reib
    -0.13
    inspace
    -0.13
    opy
    -0.13
    ensch
    -0.13
    ĵĺ
    -0.13
     éļ
    -0.13
    Ā
    -0.13
    POSITIVE LOGITS
     already
    0.26
    Already
    0.22
    already
    0.21
     Already
    0.20
     has
    0.19
     cannot
    0.17
     have
    0.16
     Weg
    0.16
     certainly
    0.15
    å·²ç»ı
    0.15
    Act Density 0.258%

    No Known Activations