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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to gases and their concentrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĥĿ
    -0.15
    дина
    -0.14
    ymes
    -0.14
    ÑĢол
    -0.13
    dorf
    -0.13
     overhe
    -0.13
     Alv
    -0.13
    Ñħи
    -0.13
    ¤ij
    -0.13
     заказ
    -0.13
    POSITIVE LOGITS
    $_
    0.28
     $_
    0.27
    _{
    0.24
     _{
    0.24
    .sub
    0.23
     subscript
    0.23
    [sub
    0.22
    /sub
    0.22
    âĤ
    0.21
    âĤĤ
    0.21
    Act Density 0.033%

    No Known Activations