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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or thresholds pertaining to sizes, quantities, or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аниÑĨ
    -0.18
    urette
    -0.18
    mé
    -0.16
    BackColor
    -0.16
    icter
    -0.15
    ylv
    -0.15
     Programm
    -0.14
    ensburg
    -0.14
    undler
    -0.14
    ientos
    -0.14
    POSITIVE LOGITS
    ç´ħ
    0.16
    ibar
    0.16
     Stam
    0.15
    ell
    0.15
    æĻ´
    0.14
    红
    0.14
     phys
    0.14
     aber
    0.14
    lr
    0.14
    ihar
    0.14
    Act Density 0.013%

    No Known Activations