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

    Neuronpedia

    INDEX
    Explanations

    ranges or intervals expressed in numerical format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and" indicating connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ax
    -0.77
    iana
    -0.73
    UGH
    -0.69
    Reviewer
    -0.68
    rod
    -0.67
    «
    -0.65
    »
    -0.64
    Discuss
    -0.63
     Cosponsors
    -0.63
    :(
    -0.63
    POSITIVE LOGITS
    omsday
    0.66
    unin
    0.65
     2030
    0.64
     1830
    0.62
    cised
    0.62
     terminate
    0.61
     twenties
    0.61
    chard
    0.61
    asted
    0.60
     infinity
    0.60
    Act Density 0.044%

    No Known Activations