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

    Neuronpedia

    INDEX
    Explanations

    directional terms, such as 'left' and 'right'

    oai_token-act-pair · gpt-3.5-turbo

    directional language and phrases related to advantages and disadvantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.72
     Ging
    -0.69
     "$:/
    -0.67
     Exhibit
    -0.62
     veto
    -0.59
     CODE
    -0.59
     Orders
    -0.59
    sbm
    -0.59
     Deal
    -0.58
     Trend
    -0.58
    POSITIVE LOGITS
     extent
    1.15
    venge
    1.02
     detriment
    0.92
    livion
    0.76
     heights
    0.76
     tune
    0.75
     fullest
    0.74
    ulkan
    0.74
     lengths
    0.73
    rouse
    0.69
    Act Density 0.234%

    No Known Activations