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

    Neuronpedia

    INDEX
    Explanations

    words related to colors and labels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to classification and grading of items, particularly in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Behind
    -0.56
     Fres
    -0.56
    juries
    -0.55
    etsy
    -0.53
    eches
    -0.53
     sting
    -0.53
    ushes
    -0.53
    leted
    -0.52
    advert
    -0.52
     Torn
    -0.51
    POSITIVE LOGITS
    +.
    1.03
     depending
    1.00
     unless
    0.97
     when
    0.89
     again
    0.86
    *.
    0.85
     due
    0.82
     whenever
    0.82
    -.
    0.82
     regardless
    0.82
    Act Density 0.398%

    No Known Activations