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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hyp
    -0.79
     Spectre
    -0.76
    crim
    -0.73
    ðĿ
    -0.72
     crim
    -0.72
    issan
    -0.71
     som
    -0.70
     cris
    -0.70
    oons
    -0.69
    trak
    -0.69
    POSITIVE LOGITS
     Be
    1.89
    Be
    1.65
     BE
    1.48
     Beet
    1.45
    be
    1.43
    BE
    1.42
     Bee
    1.42
    Bey
    1.41
     Becker
    1.41
     Beard
    1.38
    Act Density 0.254%

    No Known Activations