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

    Neuronpedia

    INDEX
    Explanations

    definite articles followed by capitalized words

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its variations as part of various phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     without
    -0.73
    perse
    -0.73
    /"
    -0.70
     patiently
    -0.69
    alone
    -0.68
    iod
    -0.67
    —-
    -0.67
    --+
    -0.66
    eno
    -0.65
     according
    -0.65
    POSITIVE LOGITS
    oret
    1.61
    resa
    1.39
    odore
    1.31
    orem
    1.25
    ories
    1.24
    atre
    1.20
     easiest
    1.06
     biggest
    1.04
     hardest
    1.03
     simplest
    1.01
    Act Density 0.295%

    No Known Activations