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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _inches
    -0.15
    them
    -0.15
    ãģª
    -0.15
    .fhir
    -0.14
    svc
    -0.14
    nya
    -0.14
    notated
    -0.13
    اذ
    -0.13
    ulis
    -0.13
    ess
    -0.13
    POSITIVE LOGITS
     again
    0.46
    again
    0.38
     Upon
    0.34
     upon
    0.33
     Again
    0.33
    Again
    0.32
    Upon
    0.30
    /if
    0.30
    upon
    0.30
    AGAIN
    0.26
    Act Density 0.033%

    No Known Activations