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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluations and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ss
    -0.18
    704
    -0.17
    cert
    -0.16
    ser
    -0.15
    stant
    -0.15
    ov
    -0.15
    velop
    -0.15
    _NAMESPACE
    -0.15
    cer
    -0.15
    sert
    -0.15
    POSITIVE LOGITS
    osu
    0.18
    dzi
    0.17
    heets
    0.17
    adt
    0.16
    dol
    0.16
    dcc
    0.15
    наÑħ
    0.15
    dal
    0.15
    med
    0.15
    rong
    0.15
    Act Density 0.402%

    No Known Activations