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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical terminology and symbols used in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĪ¦
    -0.95
     enthusi
    -0.79
    senal
    -0.79
     newsp
    -0.72
     Breach
    -0.71
    MSN
    -0.71
    idelines
    -0.71
    twitch
    -0.70
    ModLoader
    -0.69
     laun
    -0.69
    POSITIVE LOGITS
     :=
    0.94
     âĩ
    0.93
     =>
    0.92
    =>
    0.91
     expr
    0.91
     ->
    0.91
     &&
    0.89
    expr
    0.87
     foo
    0.86
    seq
    0.85
    Act Density 0.138%

    No Known Activations