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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doll
    -0.18
    .Designer
    -0.16
     صÙĨ
    -0.15
    è©
    -0.15
    åł¡
    -0.15
     predecess
    -0.15
    ç«ĭãģ¦
    -0.15
    eniable
    -0.15
     Bam
    -0.14
    zcze
    -0.14
    POSITIVE LOGITS
    488
    0.16
     abs
    0.15
    äºķ
    0.14
    azu
    0.14
    imi
    0.14
     ,
    0.14
     distracted
    0.14
    èĦ
    0.14
     Evening
    0.14
    0.13
    Act Density 0.102%

    No Known Activations