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

    Neuronpedia

    INDEX
    Explanations

    references to measurements or evaluations related to effectiveness and increases/decreases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.95
     myſelf
    -0.93
    ſelf
    -0.86
     Jefus
    -0.85
     houſe
    -0.83
    ſhip
    -0.82
     iſt
    -0.79
     ſtate
    -0.79
     faſt
    -0.78
    oa̍t
    -0.77
    POSITIVE LOGITS
    。
    0.60
    .
    0.55
    CodeAttribute
    0.55
    ，
    0.54
    k
    0.51
    EndContext
    0.51
     pájaros
    0.50
    matchCondition
    0.50
    ！
    0.50
    梅
    0.49
    Act Density 0.065%

    No Known Activations