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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific letters or sections of formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.87
     compe
    -0.79
     physic
    -0.76
    etheless
    -0.75
     parity
    -0.72
     Extras
    -0.68
     perfection
    -0.67
    76561
    -0.67
     trave
    -0.66
    anwhile
    -0.66
    POSITIVE LOGITS
    iest
    0.93
    leys
    0.89
    onian
    0.87
    intern
    0.87
    hest
    0.86
    venth
    0.85
    icer
    0.84
    est
    0.83
    agame
    0.83
    ospels
    0.82
    Act Density 0.294%

    No Known Activations