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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases in a mix of languages, particularly informal expressions and emojis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.75
     
    -0.48
     referenties
    -0.47
    +#+#
    -0.47
    AutoScaleMode
    -0.46
     виправивши
    -0.45
    مراجع
    -0.45
     StatefulWidget
    -0.45
     שוליים
    -0.45
    expandindo
    -0.44
    POSITIVE LOGITS
    colorPrimary
    0.46
     swear
    0.43
     medulla
    0.42
     chặt
    0.40
     black
    0.39
     Schna
    0.38
     squatting
    0.38
     funny
    0.37
     dignité
    0.37
     swears
    0.36
    Act Density 0.009%

    No Known Activations