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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational interactions among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vetica
    -0.16
    _ASSUME
    -0.15
    δά
    -0.15
     coquine
    -0.14
    íĥģ
    -0.14
    orum
    -0.14
    .until
    -0.14
    ecycle
    -0.14
    vider
    -0.14
    dge
    -0.14
    POSITIVE LOGITS
     done
    0.29
    ain
    0.28
     been
    0.28
     Ain
    0.27
    AIN
    0.26
     don
    0.25
     seen
    0.24
     ain
    0.24
     Cain
    0.23
     gonna
    0.23
    Act Density 0.299%

    No Known Activations