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

    Neuronpedia

    INDEX
    Explanations

    references to alternative scenarios or outcomes in comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amba
    -0.15
    ervers
    -0.15
    reek
    -0.15
    oux
    -0.15
    lis
    -0.15
    lot
    -0.15
    reta
    -0.14
    illy
    -0.14
    istas
    -0.14
    SOR
    -0.14
    POSITIVE LOGITS
     besides
    0.21
    inois
    0.17
    wise
    0.16
    _than
    0.16
    ìłĢ
    0.16
     Besides
    0.16
    -than
    0.15
    ëĿ¼ëıĦ
    0.15
     than
    0.15
    kind
    0.15
    Act Density 0.017%

    No Known Activations