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

    Neuronpedia

    INDEX
    Explanations

    instructional phrases or attributions to authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letcher
    -0.14
    berger
    -0.14
    aku
    -0.14
    amiliar
    -0.14
    utin
    -0.14
    Ñīик
    -0.14
    plex
    -0.13
    sse
    -0.13
    еÑĦ
    -0.13
    ÄĽn
    -0.13
    POSITIVE LOGITS
    ÏĦομα
    0.18
    vak
    0.15
    isay
    0.14
    utut
    0.14
    omik
    0.13
    traction
    0.13
    ££
    0.13
    ystack
    0.13
    dül
    0.13
     rodin
    0.12
    Act Density 0.008%

    No Known Activations