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

    Neuronpedia

    INDEX
    Explanations

    actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles related to causation or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.79
    rina
    -0.68
     presided
    -0.60
    ----------
    -0.60
    Flags
    -0.58
    nai
    -0.57
    swick
    -0.56
     scrimmage
    -0.56
    Hen
    -0.56
    UGH
    -0.55
    POSITIVE LOGITS
    hift
    1.08
     sure
    1.02
     sense
    0.98
     it
    0.85
     mockery
    0.74
     them
    0.73
     landfall
    0.72
     matters
    0.68
    phas
    0.66
    orno
    0.66
    Act Density 0.089%

    No Known Activations