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

    Neuronpedia

    INDEX
    Explanations

    terms related to unique identifiers or designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cq
    -0.17
    ayah
    -0.17
    haven
    -0.16
    onec
    -0.16
    illion
    -0.16
    rz
    -0.15
    .scalablytyped
    -0.15
    ãĤĪ
    -0.14
    queda
    -0.14
    ington
    -0.14
    POSITIVE LOGITS
    rian
    0.17
    icals
    0.16
     NAS
    0.15
    alach
    0.15
    ilip
    0.15
    ther
    0.14
    bad
    0.14
    epy
    0.14
    blas
    0.14
    _guard
    0.14
    Act Density 0.021%

    No Known Activations