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

    Neuronpedia

    INDEX
    Explanations

    instances where an action or event is repeated

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "twice" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.83
    ettle
    -0.79
    CHAT
    -0.78
    Trend
    -0.77
    ogi
    -0.76
    andr
    -0.73
    OTOS
    -0.72
    ollen
    -0.72
    ERAL
    -0.70
    é¾
    -0.69
    POSITIVE LOGITS
    theless
    0.87
     consecut
    0.86
     thirds
    0.83
    fold
    0.74
     redes
    0.70
     halves
    0.67
     dozen
    0.67
     dipping
    0.67
     blinded
    0.66
     consecutive
    0.63
    Act Density 0.021%

    No Known Activations