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

    Neuronpedia

    INDEX
    Explanations

    references to metrics and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.16
    assen
    -0.16
    iren
    -0.15
    maal
    -0.15
    ings
    -0.15
    ties
    -0.15
    ilon
    -0.15
    igraphy
    -0.14
    leigh
    -0.14
    ť
    -0.14
    POSITIVE LOGITS
    ally
    0.25
    ALLY
    0.22
    ágenes
    0.18
    uen
    0.17
    ting
    0.16
    avers
    0.16
    preter
    0.16
    ters
    0.16
    ayer
    0.16
    imb
    0.15
    Act Density 0.029%

    No Known Activations