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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individuals in a social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     encor
    -0.48
     Anf
    -0.46
    doin
    -0.42
     huh
    -0.42
    nalpot
    -0.41
     Carson
    -0.40
    Demografie
    -0.40
    Amen
    -0.40
     railroad
    -0.40
    Carson
    -0.39
    POSITIVE LOGITS
    ).__
    0.65
    "));
    0.58
     kaynağından
    0.57
    ModelSerializer
    0.57
    IMENT
    0.57
    исленность
    0.57
    PARTIC
    0.57
    enumii
    0.56
    scrapy
    0.56
     Humphries
    0.56
    Act Density 0.113%

    No Known Activations