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

    Neuronpedia

    INDEX
    Explanations

    programming code symbols and syntax

    oai_token-act-pair · gpt-3.5-turbo

    symbols and formatting elements commonly found in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cle
    -0.67
     travers
    -0.66
     manif
    -0.65
     glac
    -0.65
     Vale
    -0.63
     virginity
    -0.62
     Cind
    -0.62
     Highlands
    -0.62
    pillar
    -0.61
     Walton
    -0.61
    POSITIVE LOGITS
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.89
     SHARES
    0.85
    maxwell
    0.79
    mosp
    0.76
     :=
    0.76
    =#
    0.75
    asionally
    0.74
    anyahu
    0.74
     References
    0.74
    ĻĤ
    0.74
    Act Density 0.137%

    No Known Activations