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

    Neuronpedia

    INDEX
    Explanations

    references to activity and avoidance in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.67
     ſche
    -0.59
    adaptiveStyles
    -0.59
    Legături
    -0.56
     pleaſure
    -0.56
    kring
    -0.54
     незавершена
    -0.54
    lgari
    -0.52
    neſs
    -0.50
     navideñas
    -0.50
    POSITIVE LOGITS
    Activity
    0.54
     avoided
    0.47
     independence
    0.47
     omission
    0.45
     proportion
    0.44
     shift
    0.44
     avoiding
    0.42
    AppCompat
    0.41
     avoid
    0.40
     independ
    0.39
    Act Density 0.196%

    No Known Activations