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

    Neuronpedia

    INDEX
    Explanations

    the word "themselves" within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership or self-referential expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yar
    -0.74
    Dispatch
    -0.73
    ammy
    -0.73
    olid
    -0.72
    =-=-=-=-=-=-=-=-
    -0.69
     Syndicate
    -0.68
    oleon
    -0.67
    emis
    -0.67
    ropolis
    -0.66
    rop
    -0.66
    POSITIVE LOGITS
     belonged
    0.76
     outwe
    0.72
     belong
    0.70
     extinguished
    0.70
     validated
    0.70
     wors
    0.69
     contained
    0.69
     proport
    0.68
     worshipped
    0.68
     extingu
    0.68
    Act Density 0.034%

    No Known Activations