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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¡
    -0.79
    ãģ®éŃĶ
    -0.75
    ï¸
    -0.75
    ÙIJ
    -0.66
    ãĤ¨ãĥ«
    -0.66
    ãĥİ
    -0.66
     largeDownload
    -0.66
    ãĤ§
    -0.65
    ãĤ¶
    -0.64
    Û
    -0.63
    POSITIVE LOGITS
     Lans
    0.70
     Variable
    0.63
     DSL
    0.63
     Penalty
    0.58
     Rebel
    0.58
    elman
    0.57
     Ass
    0.57
     Decl
    0.57
    cens
    0.57
    ocus
    0.56
    Act Density 0.353%

    No Known Activations