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

    Neuronpedia

    INDEX
    Explanations

    non-standard characters that may have been introduced due to encoding issues

    oai_token-act-pair · gpt-3.5-turbo

    numerical values in the context of financial or economic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.81
    lest
    -0.62
    boro
    -0.61
    lections
    -0.60
    rad
    -0.58
    aeda
    -0.56
    vale
    -0.55
     smile
    -0.55
    ibia
    -0.55
     compass
    -0.55
    POSITIVE LOGITS
    However
    0.85
    Asked
    0.83
    Earlier
    0.82
     Inqu
    0.81
    Meanwhile
    0.81
    Scroll
    0.74
    Write
    0.73
    Shape
    0.71
    Related
    0.70
    Refer
    0.70
    Act Density 0.406%

    No Known Activations