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

    Neuronpedia

    INDEX
    Explanations

    instances of characters engaging in social interactions or exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.18
    озв
    -0.16
    apore
    -0.15
    antz
    -0.14
    umper
    -0.14
    ONUS
    -0.14
    Ñģли
    -0.14
    ίζ
    -0.13
    ини
    -0.13
    thon
    -0.13
    POSITIVE LOGITS
     knowing
    0.23
     resigned
    0.23
     satisfied
    0.21
     quick
    0.20
     practiced
    0.20
     look
    0.20
     sheep
    0.19
     concerned
    0.19
     defeated
    0.19
     firm
    0.19
    Act Density 0.152%

    No Known Activations