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

    Neuronpedia

    INDEX
    Explanations

    specific syntax or symbols used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    760
    -0.17
    аÑĢÑħ
    -0.15
    hana
    -0.14
    неннÑı
    -0.14
    mans
    -0.14
     Cri
    -0.14
    ripe
    -0.14
     Uhr
    -0.14
    fbe
    -0.14
    ricks
    -0.14
    POSITIVE LOGITS
    tae
    0.17
    OPSIS
    0.14
    bone
    0.14
    .Override
    0.13
    quotes
    0.13
     favor
    0.13
    hetto
    0.13
    .libs
    0.13
    GRESS
    0.13
    ka
    0.13
    Act Density 0.008%

    No Known Activations