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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and humor in responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elemField
    -0.98
     surla
    -0.83
    contentLoaded
    -0.82
    存于互联网档案馆
    -0.81
     ―――――
    -0.80
    rungsseite
    -0.79
    AndEndTag
    -0.78
    afficheront
    -0.76
    RenderAtEndOf
    -0.74
     الرياضيه
    -0.73
    POSITIVE LOGITS
     I
    0.44
    I
    0.40
    maybe
    0.38
    oh
    0.38
    my
    0.37
     maybe
    0.35
     Maybe
    0.35
    T
    0.34
     zumal
    0.34
    K
    0.34
    Act Density 0.321%

    No Known Activations