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

    Neuronpedia

    INDEX
    Explanations

    words with high frequencies within a specific context or grammatical category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pNet
    -0.16
     Balt
    -0.14
    915
    -0.14
     Kinder
    -0.14
    _Private
    -0.14
    edo
    -0.14
    hu
    -0.14
    anguard
    -0.14
    ÚĨ
    -0.13
    door
    -0.13
    POSITIVE LOGITS
    ames
    0.18
    abant
    0.15
    mesh
    0.13
    toISOString
    0.13
    pha
    0.13
     Whites
    0.13
    abit
    0.13
     mesh
    0.13
    anno
    0.13
    _fwd
    0.13
    Act Density 0.114%

    No Known Activations