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

    Neuronpedia

    INDEX
    Explanations

    approximate numerical values

    oai_token-act-pair · gpt-3.5-turbo

    the word "roughly" indicating approximations or estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TB
    -0.73
    ieu
    -0.71
    Reviewer
    -0.71
    ters
    -0.70
    YES
    -0.70
    iments
    -0.70
    oa
    -0.68
    oli
    -0.67
     Shame
    -0.65
    idy
    -0.65
    POSITIVE LOGITS
     analogous
    0.88
    Ĥİ
    0.81
     approximate
    0.80
    Ń·
    0.79
     speaking
    0.77
     equivalent
    0.76
     820
    0.76
     sized
    0.73
    ãĤ©
    0.71
     contempor
    0.71
    Act Density 0.020%

    No Known Activations