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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and reactions shared in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbggenerated
    -0.62
    Porque
    -0.59
     }^{*}$
    -0.58
    /**/*.
    -0.56
     ͜ʖ
    -0.54
    ידע
    -0.52
     onAnimation
    -0.52
     ویکی‌پدیای
    -0.52
    囗
    -0.52
    IntoConstraints
    -0.52
    POSITIVE LOGITS
     Earlier
    0.81
    Earlier
    0.78
    Meanwhile
    0.74
     Meanwhile
    0.74
     meanwhile
    0.73
     Roskov
    0.70
    Fans
    0.68
     earlier
    0.68
     recentemente
    0.65
     Fans
    0.63
    Act Density 0.069%

    No Known Activations