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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that involve contrasting options or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a comparison or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursday
    -0.91
    igers
    -0.80
    iday
    -0.72
    bank
    -0.71
    ament
    -0.71
    uesday
    -0.71
    IGHT
    -0.69
    IDER
    -0.67
    bell
    -0.66
    igator
    -0.66
    POSITIVE LOGITS
     Marketable
    0.92
    acle
    0.71
     equivalents
    0.71
     dispose
    0.70
     equivalent
    0.69
     acquies
    0.67
    acles
    0.67
     guiIcon
    0.67
    Downloadha
    0.66
     erase
    0.66
    Act Density 0.064%

    No Known Activations