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

    Neuronpedia

    INDEX
    Explanations

    complex narratives involving internal conflict and emotional struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     odv
    -0.16
    ราย
    -0.15
    APPER
    -0.15
    ORED
    -0.15
    erais
    -0.15
    lop
    -0.15
    öz
    -0.14
    éŀ
    -0.14
     Ú¯ÙĦ
    -0.14
     Swords
    -0.14
    POSITIVE LOGITS
     horn
    0.18
     push
    0.16
     seal
    0.16
     temptation
    0.16
    horn
    0.16
     blinded
    0.15
    push
    0.15
     mess
    0.15
    tempt
    0.15
    -push
    0.15
    Act Density 0.017%

    No Known Activations