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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions and symbols

    oai_token-act-pair · gpt-3.5-turbo

    mathematical terms and concepts related to probabilities and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whistlebl
    -0.74
     mentors
    -0.71
     Jarvis
    -0.71
     curated
    -0.70
    etooth
    -0.68
     vetted
    -0.67
     elders
    -0.66
     scares
    -0.66
    ookie
    -0.66
     stink
    -0.65
    POSITIVE LOGITS
     multiplying
    1.27
     subtract
    1.27
     multiplication
    1.26
     equation
    1.25
     multiply
    1.23
     Suppose
    1.23
     $$
    1.18
     Calcul
    1.18
     {\
    1.15
     exponent
    1.15
    Act Density 0.279%

    No Known Activations