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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases indicating temporal relationships or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogan
    -0.15
    Äįek
    -0.15
     Mine
    -0.15
    -bordered
    -0.14
    968
    -0.14
    oleÄį
    -0.13
    erior
    -0.13
    ock
    -0.13
    cad
    -0.13
    elm
    -0.13
    POSITIVE LOGITS
    ensch
    0.18
     applied
    0.17
     compared
    0.17
     used
    0.17
     care
    0.15
     Applied
    0.15
    ory
    0.15
    uru
    0.14
    fonts
    0.14
    Å¡ku
    0.14
    Act Density 0.176%

    No Known Activations