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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical confidence indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crosby
    -0.18
    ÑĢеÑħ
    -0.16
    Closure
    -0.16
    cura
    -0.16
    ÏĨι
    -0.16
    Compatibility
    -0.16
     Cassidy
    -0.15
    eÄį
    -0.15
    emes
    -0.15
     Criterion
    -0.15
    POSITIVE LOGITS
    .Con
    0.43
    _Con
    0.42
     CON
    0.41
    -con
    0.39
     Con
    0.38
    .CON
    0.37
    Con
    0.36
    _con
    0.36
     Kon
    0.35
    con
    0.35
    Act Density 0.012%

    No Known Activations