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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating some kind of quality or type

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating types of classifications or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fs
    -1.01
    anders
    -0.99
    izons
    -0.95
    stones
    -0.93
    ents
    -0.93
    naires
    -0.93
    ves
    -0.92
    users
    -0.91
    months
    -0.90
    parts
    -0.89
    POSITIVE LOGITS
     consolation
    1.06
     afterlife
    1.00
     enlightenment
    1.00
     miraculous
    0.95
     miracle
    0.95
     immortality
    0.95
     intermediary
    0.93
     retribution
    0.93
     unofficial
    0.92
     apology
    0.92
    Act Density 0.066%

    No Known Activations