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

    Neuronpedia

    INDEX
    Explanations

    references to actions, conditions, or concerns expressed in a conversational manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eldorf
    -0.16
     ¶
    -0.14
    ÑĨÑĮ
    -0.14
    ëĮ
    -0.14
    chyb
    -0.14
    ÙĨداÙĨ
    -0.13
    eken
    -0.13
    ochond
    -0.13
    storm
    -0.13
     charges
    -0.13
    POSITIVE LOGITS
    /../
    0.15
    olas
    0.14
    dorf
    0.14
    PCR
    0.14
    bid
    0.14
    agal
    0.14
    ypad
    0.14
    44
    0.14
    ystack
    0.13
     starred
    0.13
    Act Density 0.324%

    No Known Activations