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

    Neuronpedia

    INDEX
    Explanations

    occurrences of academic or scientific discussions and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rias
    -0.19
    опол
    -0.17
    reon
    -0.17
    rac
    -0.16
    ERO
    -0.16
    stm
    -0.15
    ourcem
    -0.15
    еÑĢо
    -0.15
    wald
    -0.15
    aroo
    -0.15
    POSITIVE LOGITS
    azon
    0.16
    Ä±ÅŁÄ±k
    0.15
    udo
    0.15
    475
    0.14
    457
    0.14
     lives
    0.14
    ByPrimaryKey
    0.14
    igne
    0.14
     Lives
    0.14
    .ask
    0.14
    Act Density 0.036%

    No Known Activations