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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, modifications, and increased quantities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģİ
    -0.16
    804
    -0.15
     cra
    -0.14
    iec
    -0.14
    ahoo
    -0.14
    373
    -0.14
    elay
    -0.14
    ä¸ĭæĿ¥
    -0.14
    StateException
    -0.13
     queryset
    -0.13
    POSITIVE LOGITS
     than
    0.19
    than
    0.19
    -than
    0.18
     niż
    0.18
     compens
    0.18
     compensate
    0.16
    _than
    0.16
     compensation
    0.16
    (extra
    0.16
     compensated
    0.15
    Act Density 0.229%

    No Known Activations