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

    Neuronpedia

    INDEX
    Explanations

    terms related to digital technology

    oai_token-act-pair · gpt-3.5-turbo

    references to the digital world and digital content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -1.02
    IELD
    -0.88
    etta
    -0.80
    ortium
    -0.80
    ered
    -0.78
     Strauss
    -0.77
    hiro
    -0.75
    olini
    -0.74
    hov
    -0.73
    stad
    -0.73
    POSITIVE LOGITS
    netic
    0.95
    ized
    0.91
    Ocean
    0.89
    ization
    0.89
     currency
    0.85
    isation
    0.85
     footprint
    0.81
    olor
    0.80
     savvy
    0.79
    izable
    0.78
    Act Density 0.015%

    No Known Activations