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

    Neuronpedia

    INDEX
    Explanations

    numerical rankings or scores associated with language apps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascade
    -0.17
    lingen
    -0.16
    ukan
    -0.15
    ất
    -0.14
    UMENT
    -0.14
    ument
    -0.14
    abay
    -0.14
     Osc
    -0.14
    ijk
    -0.14
    /forum
    -0.14
    POSITIVE LOGITS
    toc
    0.18
    ToObject
    0.17
    ãĥ³ãĥĶ
    0.16
    /Internal
    0.15
    kin
    0.14
    _PWR
    0.14
    ÑĸÑĹв
    0.13
    ÑĪиб
    0.13
    $MESS
    0.13
    oden
    0.13
    Act Density 0.007%

    No Known Activations