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

    Neuronpedia

    INDEX
    Explanations

    terms associated with computational metrics and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XIII
    -0.90
     Wednesday
    -0.86
    Wednesday
    -0.84
     WEDNESDAY
    -0.83
    XIII
    -0.81
     Thirteenth
    -0.79
    WEDNESDAY
    -0.78
    XXIII
    -0.76
     Shepard
    -0.76
     Wed
    -0.75
    POSITIVE LOGITS
     McPherson
    0.74
     Bick
    0.65
    lwjgl
    0.63
    CRI
    0.62
     McCl
    0.62
     Perrin
    0.61
     Stefano
    0.61
     CRI
    0.61
    Stefano
    0.61
     Schwan
    0.60
    Act Density 1.978%

    No Known Activations