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

    Neuronpedia

    INDEX
    Explanations

    instances of an action or event occurring two times

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "twice."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.88
    ogi
    -0.84
    CHAT
    -0.79
    ettle
    -0.77
    Trend
    -0.74
    AMI
    -0.73
    OTOS
    -0.73
    rollers
    -0.72
    DIT
    -0.72
    vy
    -0.72
    POSITIVE LOGITS
    theless
    0.94
     consecut
    0.88
     thirds
    0.75
    fold
    0.73
     dipping
    0.70
     dozen
    0.67
     blinded
    0.65
     apiece
    0.65
     overlapping
    0.63
     consecutive
    0.62
    Act Density 0.022%

    No Known Activations