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

    Neuronpedia

    INDEX
    Explanations

    terms related to immediacy or urgency

    oai_token-act-pair · gpt-3.5-turbo

    instances of immediate effects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bris
    -0.72
    zai
    -0.70
    mart
    -0.70
    iasco
    -0.69
    radical
    -0.68
     disasters
    -0.68
    artifacts
    -0.68
    apons
    -0.66
    izophren
    -0.65
    zynski
    -0.64
    POSITIVE LOGITS
     vs
    0.79
     =
    0.71
     alone
    0.71
     versus
    0.70
     <-
    0.69
    âĨĴ
    0.67
     âĨĴ
    0.63
    vs
    0.63
     Autob
    0.60
     ÃĹ
    0.59
    Act Density 1.006%

    No Known Activations