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

    Neuronpedia

    INDEX
    Explanations

    terms related to probability and chance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and probabilistic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     palms
    -0.75
     Valhalla
    -0.70
     Hust
    -0.68
    OWN
    -0.64
    ideshow
    -0.62
     Peninsula
    -0.62
     Sparrow
    -0.61
     cheeks
    -0.59
     Valent
    -0.59
    overs
    -0.57
    POSITIVE LOGITS
    iotics
    1.36
    iotic
    1.27
    abil
    1.22
    osc
    1.10
    abilities
    0.96
    bably
    0.96
    imon
    0.95
    bly
    0.92
    orship
    0.91
    orate
    0.88
    Act Density 0.043%

    No Known Activations