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

    Neuronpedia

    INDEX
    Explanations

    negative restrictions and prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    824
    -0.15
    å»·
    -0.15
    SOR
    -0.15
     prov
    -0.15
    eyin
    -0.15
    aday
    -0.14
     Ital
    -0.14
    æİ¥çĿĢ
    -0.14
    vailable
    -0.14
     tap
    -0.14
    POSITIVE LOGITS
     unless
    0.14
     Baum
    0.14
    737
    0.14
    mind
    0.14
    _ANY
    0.14
    .createClass
    0.14
    ordan
    0.13
     nÃło
    0.13
     meas
    0.13
    AME
    0.13
    Act Density 0.087%

    No Known Activations