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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons of past and present situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ots
    -0.16
    awi
    -0.15
    671
    -0.14
     neat
    -0.14
    635
    -0.14
     Hardcore
    -0.14
     Dude
    -0.14
     Harding
    -0.14
    613
    -0.14
    aintenance
    -0.13
    POSITIVE LOGITS
    pei
    0.15
    ddy
    0.15
    odate
    0.14
    رÙĪÙĩ
    0.14
    imple
    0.14
    obic
    0.14
     Calder
    0.13
    BOOT
    0.13
    uracy
    0.13
    ights
    0.13
    Act Density 0.085%

    No Known Activations