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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers and references in academic or research-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itag
    -0.16
    itzer
    -0.16
    pillar
    -0.16
    æĭħå½ĵ
    -0.15
    idian
    -0.15
    leys
    -0.15
    ilis
    -0.14
    INO
    -0.14
    523
    -0.14
    gv
    -0.14
    POSITIVE LOGITS
    unft
    0.18
     Emin
    0.16
    iste
    0.14
    -preview
    0.14
    ampo
    0.14
    abela
    0.14
     aggress
    0.14
    ιθ
    0.14
    atego
    0.14
     Monte
    0.14
    Act Density 0.002%

    No Known Activations