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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific measurement or bias-related terminology in technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.19
     in
    -0.18
     the
    -0.18
     _
    -0.17
     to
    -0.17
     has
    -0.16
     a
    -0.16
     for
    -0.16
     and
    -0.15
     special
    -0.15
    POSITIVE LOGITS
    0.32
    0.19
    0.17
    NULL
    0.16
    ÑĥÑĢÑĭ
    0.14
    Ñĩа
    0.14
    _inches
    0.14
    agen
    0.14
    cha
    0.13
    clo
    0.13
    Act Density 0.004%

    No Known Activations