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

    Neuronpedia

    INDEX
    Explanations

    words related to probabilities and likelihoods

    oai_token-act-pair · gpt-3.5-turbo

    terms related to probability and statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Valhalla
    -0.81
     palms
    -0.79
    holders
    -0.72
    overs
    -0.66
     Darling
    -0.63
     Alps
    -0.61
    dust
    -0.61
     Skies
    -0.60
     Lumpur
    -0.59
     blindness
    -0.59
    POSITIVE LOGITS
    iotics
    1.25
    iotic
    1.21
    abil
    1.01
    bly
    0.91
    icy
    0.89
    iciary
    0.88
    abilities
    0.85
    osc
    0.85
    itely
    0.81
    ptr
    0.79
    Act Density 0.016%

    No Known Activations