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

    Neuronpedia

    INDEX
    Explanations

    instances of crucial decision-making or speculative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĩно
    -0.16
    åħ´
    -0.14
     CR
    -0.14
    Solid
    -0.14
    oup
    -0.14
    åĶĩ
    -0.14
    nell
    -0.14
    iap
    -0.14
    retty
    -0.13
     зн
    -0.13
    POSITIVE LOGITS
    rve
    0.15
     Toe
    0.15
    ftar
    0.14
     Bowling
    0.14
    arium
    0.14
    ifice
    0.14
     å¯
    0.14
     wherever
    0.14
    Ïīμα
    0.14
    913
    0.14
    Act Density 0.000%

    No Known Activations