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

    Neuronpedia

    INDEX
    Explanations

    segments of text with ellipses or other unusual punctuation patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plier
    -0.19
    .LA
    -0.16
    iew
    -0.15
    ises
    -0.15
    .Slf
    -0.14
    imes
    -0.14
    meg
    -0.14
    tam
    -0.14
    ä¼´
    -0.14
    mise
    -0.14
    POSITIVE LOGITS
    datal
    0.17
    оÑħ
    0.16
    achel
    0.15
    NSS
    0.14
     sac
    0.14
     abstract
    0.13
     distortion
    0.13
    sha
    0.13
    115
    0.13
    ocha
    0.13
    Act Density 0.021%

    No Known Activations