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

    Neuronpedia

    INDEX
    Explanations

    references to folders in a computing context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λÏī
    -0.17
    utt
    -0.16
    outu
    -0.15
    engin
    -0.15
    کرد
    -0.14
    fone
    -0.14
    opsis
    -0.14
    ceae
    -0.14
    fos
    -0.14
    اÙĦÙĩ
    -0.13
    POSITIVE LOGITS
    rible
    0.17
    rouw
    0.16
    oen
    0.16
     пÑĢиÑĤ
    0.16
    icide
    0.16
    sten
    0.15
     Abram
    0.15
    stack
    0.15
    ikh
    0.14
    iage
    0.14
    Act Density 0.004%

    No Known Activations