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

    Neuronpedia

    INDEX
    Explanations

    words related to widespread negative conditions or issues

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various forms of affliction or adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.84
    ibling
    -0.78
    ettel
    -0.76
    ccording
    -0.76
    ynthesis
    -0.76
    ndra
    -0.75
    ials
    -0.73
    Streamer
    -0.73
    ramid
    -0.72
    cyclop
    -0.71
    POSITIVE LOGITS
     plague
    1.29
     plag
    0.90
     Plague
    0.88
     blight
    0.86
     scourge
    0.85
    bug
    0.80
    bugs
    0.77
     menace
    0.77
    lords
    0.76
     infect
    0.76
    Act Density 0.013%

    No Known Activations