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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental accuracy and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Weiner
    -0.15
    andes
    -0.15
    اÙĨÙĩ
    -0.15
    enheim
    -0.14
     Gomez
    -0.14
    .Automation
    -0.13
    รà¸ģ
    -0.13
     Cly
    -0.13
    CAA
    -0.13
     Ow
    -0.13
    POSITIVE LOGITS
     experimental
    0.19
     match
    0.19
    enton
    0.19
    experimental
    0.18
    lesh
    0.18
     correct
    0.17
     matches
    0.17
    _hooks
    0.17
    ertest
    0.17
     agreement
    0.16
    Act Density 0.100%

    No Known Activations