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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve conditional statements or refer to specific cases and examples in legal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     $\
    -0.48
     t
    -0.48
     et
    -0.48
    de
    -0.47
    m
    -0.46
    bar
    -0.45
    #:
    -0.45
    westen
    -0.45
     lo
    -0.45
     he
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.96
    клопе
    0.93
    RectangleBorder
    0.86
    verwijspagina
    0.84
    ſelf
    0.81
     Majefty
    0.81
     ་་
    0.80
     FontWeight
    0.80
     itſelf
    0.79
     myſelf
    0.78
    Act Density 0.956%

    No Known Activations