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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preparation or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating preparation or anticipation for an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ochet
    -0.69
    oret
    -0.69
    aspx
    -0.67
    operated
    -0.64
     Bots
    -0.61
     Luxem
    -0.60
     fault
    -0.59
     outstanding
    -0.59
     tam
    -0.59
     translator
    -0.57
    POSITIVE LOGITS
    skirts
    0.95
    cair
    0.78
    ptin
    0.78
    edo
    0.77
    itta
    0.77
    ÃįÃį
    0.73
    iatus
    0.72
    atonin
    0.72
    riott
    0.72
     Idle
    0.72
    Act Density 0.027%

    No Known Activations