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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    136
    -0.15
    ulas
    -0.15
    ract
    -0.15
    chet
    -0.15
    iska
    -0.14
    件
    -0.14
    adero
    -0.14
    idend
    -0.14
    glob
    -0.14
    zin
    -0.14
    POSITIVE LOGITS
     importance
    0.25
     Importance
    0.23
     emphasis
    0.23
    phasis
    0.22
    phas
    0.22
    emphasis
    0.20
    uated
    0.20
     upon
    0.18
     emphasize
    0.17
    uating
    0.17
    Act Density 0.032%

    No Known Activations