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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant consequences or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.16
     Relax
    -0.15
    kart
    -0.15
    otal
    -0.15
    帯
    -0.14
    anc
    -0.14
    avor
    -0.14
    emann
    -0.14
    issen
    -0.14
     Hollow
    -0.14
    POSITIVE LOGITS
    Ïħνα
    0.16
    ISR
    0.15
    uddle
    0.15
    _wire
    0.15
    ibi
    0.14
    eni
    0.14
    blr
    0.14
    айд
    0.14
    odium
    0.14
    epy
    0.14
    Act Density 0.092%

    No Known Activations