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

    Neuronpedia

    INDEX
    Explanations

    words related to significant discoveries or advancements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant advancements or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Į
    -0.80
    astern
    -0.80
    erve
    -0.77
    osuke
    -0.76
    cale
    -0.76
    gypt
    -0.76
    isphere
    -0.75
    Ĥ
    -0.75
    ateur
    -0.71
    atra
    -0.71
    POSITIVE LOGITS
    PsyNetMessage
    1.02
    stroke
    0.75
     breakthrough
    0.75
     Ambro
    0.70
    Assembly
    0.68
     breakout
    0.68
    knit
    0.65
     APR
    0.65
    Solution
    0.64
    ibles
    0.63
    Act Density 0.030%

    No Known Activations