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

    Neuronpedia

    INDEX
    Explanations

    queries or questions seeking confirmation or additional information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Coyle
    -0.52
    лева
    -0.52
     προς
    -0.52
    DebuggerNonUser
    -0.49
    לת
    -0.47
     effray
    -0.47
    wachsene
    -0.46
    ței
    -0.45
     open
    -0.45
     ora
    -0.45
    POSITIVE LOGITS
     myſelf
    0.99
     pleaſure
    0.93
    OGND
    0.91
     itſelf
    0.90
     poffe
    0.88
     nahilalakip
    0.88
     ſeveral
    0.84
     himſelf
    0.83
     uſed
    0.83
     typelib
    0.82
    Act Density 0.011%

    No Known Activations