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

    Neuronpedia

    INDEX
    Explanations

    food-related words, particularly those related to a meal like lunch

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "unch" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ministry
    -0.77
    âĹ¼
    -0.77
    wcs
    -0.73
    Naz
    -0.66
     Scientology
    -0.63
    lling
    -0.63
     differe
    -0.63
    Offic
    -0.63
    tnc
    -0.62
     Defenders
    -0.61
    POSITIVE LOGITS
    arted
    0.94
    ainment
    0.88
    atters
    0.87
    ramid
    0.87
    ies
    0.86
    osate
    0.86
    iesta
    0.85
    ifact
    0.83
    aus
    0.83
    onen
    0.82
    Act Density 0.033%

    No Known Activations