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

    Neuronpedia

    INDEX
    Explanations

    mentions of dates and significant days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -0.93
     Anſ
    -0.81
     Theſe
    -0.80
     myſelf
    -0.78
     ſch
    -0.78
     Diſ
    -0.76
     ſta
    -0.76
     Reſ
    -0.76
     dalamnya
    -0.75
     ſen
    -0.75
    POSITIVE LOGITS
    simpleType
    0.65
     forgetting
    0.58
    énario
    0.57
     CWE
    0.57
    BEFORE
    0.57
    QRST
    0.54
    adaptiveStyles
    0.54
    romyal
    0.53
    atitis
    0.53
    Abp
    0.52
    Act Density 0.175%

    No Known Activations