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

    Neuronpedia

    INDEX
    Explanations

    expressions related to identity and personal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opoulos
    -0.17
     hero
    -0.15
    çķ
    -0.15
    ë§Ŀ
    -0.14
    Notifier
    -0.13
     formal
    -0.13
    anian
    -0.13
    /*****************************************************************************↵
    -0.13
    ivan
    -0.13
    likes
    -0.13
    POSITIVE LOGITS
     DNA
    0.33
     essence
    0.32
    DNA
    0.31
     soul
    0.29
     dna
    0.29
     spirit
    0.27
    dna
    0.26
     personality
    0.25
     nature
    0.23
     souls
    0.23
    Act Density 0.033%

    No Known Activations