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

    Neuronpedia

    INDEX
    Explanations

    terms related to website URLs and online content

    oai_token-act-pair · gpt-3.5-turbo

    content related to official sites or platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.73
    hement
    -0.72
    tsky
    -0.68
    uca
    -0.65
    iously
    -0.63
    ucci
    -0.62
    hest
    -0.62
     margins
    -0.60
     bandits
    -0.58
     sovere
    -0.57
    POSITIVE LOGITS
    ³³³
    0.92
    ³³³³³³³³³³³³³³³³
    0.90
    ccording
    0.83
    Date
    0.74
    ³³³³³³³³
    0.72
    ³³
    0.72
     Decoder
    0.71
    earances
    0.71
     Allows
    0.70
    inav
    0.69
    Act Density 0.239%

    No Known Activations