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

    Neuronpedia

    INDEX
    Explanations

    occurrences where something is done or happens twice

    oai_token-act-pair · gpt-3.5-turbo

    the word "twice" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.95
    CHAT
    -0.77
    Trend
    -0.77
    ettle
    -0.76
    andr
    -0.75
    rt
    -0.73
    aceous
    -0.73
    bern
    -0.71
    ogi
    -0.69
    é¾
    -0.69
    POSITIVE LOGITS
     consecut
    0.88
    fold
    0.80
    theless
    0.80
     thirds
    0.77
     redes
    0.68
     conclud
    0.67
    soever
    0.66
     consecutive
    0.66
     blinded
    0.65
     dipping
    0.64
    Act Density 0.019%

    No Known Activations