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

    Neuronpedia

    INDEX
    Explanations

    mentions of minor-related terms in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to minor entities or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.86
    raltar
    -0.74
    igslist
    -0.69
    adr
    -0.68
    reens
    -0.68
    ichick
    -0.68
    anooga
    -0.67
    romeda
    -0.67
    leneck
    -0.66
    shell
    -0.65
    POSITIVE LOGITS
    itized
    0.91
     inconven
    0.90
     leagues
    0.89
     league
    0.83
    ities
    0.83
     deviations
    0.80
     inconvenience
    0.78
     tweaks
    0.77
     annoyance
    0.74
     adjustments
    0.74
    Act Density 0.023%

    No Known Activations