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

    Neuronpedia

    INDEX
    Explanations

    instances of tagging within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chet
    -0.16
    arium
    -0.15
    ालय
    -0.15
    uhe
    -0.15
    iky
    -0.14
    ven
    -0.14
     McCabe
    -0.14
    cla
    -0.14
    eres
    -0.14
    Ħìŀ¬
    -0.14
    POSITIVE LOGITS
    ging
    0.24
    ged
    0.22
    /tag
    0.20
    gings
    0.17
    GED
    0.17
    rou
    0.17
    GING
    0.17
    vanced
    0.17
    alog
    0.16
    zilla
    0.16
    Act Density 0.036%

    No Known Activations