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

    Neuronpedia

    INDEX
    Explanations

    mentions of upcoming events or releases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.74
    arians
    -0.74
    quit
    -0.70
    load
    -0.69
    fn
    -0.68
    pointers
    -0.68
    ibl
    -0.66
    olicy
    -0.65
    nance
    -0.65
    edly
    -0.64
    POSITIVE LOGITS
     midst
    1.65
     vicinity
    1.40
     meantime
    1.35
     aftermath
    1.31
     guise
    1.28
     same
    1.15
     absence
    1.13
     slightest
    1.13
     wake
    1.10
     middle
    1.10
    Act Density 0.989%

    No Known Activations