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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and methods for optimization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ::$_
    -0.17
    GORITH
    -0.15
    hin
    -0.15
     Draco
    -0.15
    _SCOPE
    -0.14
    gon
    -0.14
     along
    -0.13
    udded
    -0.13
    atten
    -0.13
    214
    -0.13
    POSITIVE LOGITS
    IPA
    0.16
    chn
    0.14
     lady
    0.14
    лиÑĪ
    0.14
    aget
    0.14
     NM
    0.14
    ephir
    0.14
    macen
    0.14
    oce
    0.13
    лага
    0.13
    Act Density 0.238%

    No Known Activations