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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly focusing on the term "guy"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0200
    -0.73
     srfAttach
    -0.69
    FIN
    -0.66
    ichever
    -0.65
    031
    -0.62
     ILCS
    -0.62
    BuyableInstoreAndOnline
    -0.62
     Remain
    -0.61
     Doors
    -0.59
    FINEST
    -0.58
    POSITIVE LOGITS
    hole
    0.80
    wagon
    0.75
     Ares
    0.69
     cared
    0.68
    swick
    0.67
    ery
    0.66
    has
    0.65
    iology
    0.63
    abwe
    0.63
    izer
    0.63
    Act Density 0.101%

    No Known Activations