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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative consequences or issues

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or formatting that seems to represent special symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.87
    ãģ®éŃĶ
    -0.85
    gow
    -0.76
    enburg
    -0.74
    ements
    -0.70
     compuls
    -0.68
    worthiness
    -0.66
     whichever
    -0.63
     PTS
    -0.63
    iator
    -0.62
    POSITIVE LOGITS
    ¹
    1.77
    ³
    1.71
    ¿
    1.69
    ¦
    1.64
    ¬
    1.64
    µ
    1.54
    ¾
    1.54
    ¥
    1.54
    ¸
    1.50
    ¡
    1.46
    Act Density 0.015%

    No Known Activations