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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or entities with initials

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'J' followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holders
    -0.69
    iture
    -0.68
    fman
    -0.68
    terior
    -0.66
    vana
    -0.65
    auga
    -0.64
    chwitz
    -0.64
    aults
    -0.63
    agascar
    -0.63
    milo
    -0.62
    POSITIVE LOGITS
    ournal
    0.92
     Edgar
    0.85
     Sawyer
    0.84
    Crew
    0.83
     Jonah
    0.78
    Ax
    0.78
     Marriott
    0.74
    Lo
    0.74
     Reilly
    0.71
     Simpson
    0.71
    Act Density 0.043%

    No Known Activations