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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to ratings and measurements in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !*\
    -0.72
     ***!
    -0.66
     (!)
    -0.64
    !
    -0.57
     !
    -0.54
    .’
    -0.53
    (!)
    -0.51
    .**
    -0.51
     。
    -0.51
     --
    -0.51
    POSITIVE LOGITS
     это
    0.75
    noun
    0.71
    щет
    0.69
     Part
    0.69
    ˈ
    0.68
     financières
    0.68
     vérit
    0.65
     abgerufen
    0.65
     noun
    0.65
    ----------------
    0.65
    Act Density 0.688%

    No Known Activations