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

    Neuronpedia

    INDEX
    Explanations

    lines of code or other text content that includes numbers and special characters

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gmail
    -0.62
     reinstated
    -0.62
     enthusiastic
    -0.58
     revital
    -0.57
     whip
    -0.56
     reins
    -0.55
    eus
    -0.55
     lure
    -0.54
     ens
    -0.53
     overse
    -0.53
    POSITIVE LOGITS
     partName
    0.64
     ||
    0.64
    %"
    0.63
     Caption
    0.60
     Loading
    0.60
    eri
    0.59
     Fail
    0.58
     Activate
    0.57
    SOURCE
    0.57
     Carney
    0.57
    Act Density 0.370%

    No Known Activations