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

    Neuronpedia

    INDEX
    Explanations

    steps and procedural instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rest
    -0.44
     shed
    -0.42
     bargain
    -0.41
    ronom
    -0.41
     Murray
    -0.41
     ongoing
    -0.40
     Bore
    -0.40
     اغ
    -0.39
    OLOG
    -0.39
     overnight
    -0.38
    POSITIVE LOGITS
    step
    1.08
    STEP
    0.99
    Step
    0.95
     STEP
    0.92
    steps
    0.91
     step
    0.90
     Step
    0.89
    Steps
    0.89
    STEPS
    0.85
     Schritt
    0.84
    Act Density 0.278%

    No Known Activations