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

    Neuronpedia

    INDEX
    Explanations

    specific entities or terms matching the pattern "T number."

    oai_token-act-pair · gpt-3.5-turbo

    the character "T" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.86
    EStream
    -0.79
     actionGroup
    -0.75
    76561
    -0.74
    vernment
    -0.69
     cannabin
    -0.69
     ment
    -0.68
     rounding
    -0.67
    Ĥİ
    -0.66
     Skydragon
    -0.65
    POSITIVE LOGITS
    ARGET
    1.21
    ractor
    1.16
    olkien
    1.16
    TY
    1.09
    ribute
    1.09
    aylor
    1.07
    ribune
    1.07
    ricia
    1.07
    ruck
    1.05
    ravis
    1.04
    Act Density 0.028%

    No Known Activations