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

    Neuronpedia

    INDEX
    Explanations

    technical phrases related to performance and specifications, particularly with numerical values

    oai_token-act-pair · gpt-3.5-turbo

    elements related to design and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.78
    hement
    -0.76
    tsky
    -0.69
     Vaugh
    -0.68
    dn
    -0.68
     unlucky
    -0.67
    etta
    -0.66
    baugh
    -0.64
    wen
    -0.63
    elin
    -0.62
    POSITIVE LOGITS
    Marginal
    0.85
    ccording
    0.83
    ========
    0.79
    Overview
    0.78
    ============
    0.76
    Spoiler
    0.75
    ":["
    0.74
     Generally
    0.73
     Classification
    0.73
     Removal
    0.73
    Act Density 0.143%

    No Known Activations