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

    Neuronpedia

    INDEX
    Explanations

    programming syntax related to function definitions and control structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    unzi
    -0.55
     
    -0.50
     P
    -0.47
     Inter
    -0.46
     ko
    -0.46
     fra
    -0.46
     la
    -0.45
     واس
    -0.45
     First
    -0.45
     Vor
    -0.45
    POSITIVE LOGITS
     Majefty
    0.97
     myſelf
    0.96
    IBarButtonItem
    0.87
    ſelf
    0.85
     typelib
    0.84
    kloped
    0.83
     itſelf
    0.83
     fevere
    0.82
     pleaſure
    0.82
     ivelany
    0.82
    Act Density 0.008%

    No Known Activations