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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or uncommon/gibberish words in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    terms related to utopian and dystopian concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thresholds
    -0.80
     signatures
    -0.70
     warnings
    -0.70
     microphones
    -0.69
     markings
    -0.68
     caveats
    -0.67
    votes
    -0.64
     stickers
    -0.62
     nods
    -0.62
     respondents
    -0.61
    POSITIVE LOGITS
    iphate
    0.79
    capitalist
    0.78
     organism
    0.77
    ocracy
    0.76
     institution
    0.76
    ifestyle
    0.75
    orld
    0.74
    cosystem
    0.71
    tarian
    0.71
    lite
    0.70
    Act Density 0.670%

    No Known Activations