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

    Neuronpedia

    INDEX
    Explanations

    references to signals and their qualities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Bux
    -0.74
    Климат
    -0.67
    asthan
    -0.64
    Maur
    -0.63
    DeleteBehavior
    -0.63
     Yeats
    -0.63
     memp
    -0.62
    ykite
    -0.62
     Baxter
    -0.60
    copo
    -0.60
    POSITIVE LOGITS
     Signals
    1.62
     signals
    1.57
    signals
    1.55
     Signal
    1.45
    SIGNAL
    1.38
     signal
    1.36
     SIGNAL
    1.36
    signal
    1.35
    Signals
    1.34
    Signal
    1.27
    Act Density 0.039%

    No Known Activations