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

    Neuronpedia

    INDEX
    Explanations

    numerical values or quantities specified in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "roughly" followed by numerical estimates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oa
    -0.82
    iments
    -0.69
    ysis
    -0.69
    ters
    -0.68
    YES
    -0.67
    Reviewer
    -0.67
    ieu
    -0.66
     Bomber
    -0.66
    ista
    -0.66
    TB
    -0.64
    POSITIVE LOGITS
     analogous
    0.86
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.79
     approximate
    0.78
    Ĥİ
    0.75
     equivalent
    0.75
     speaking
    0.71
     contempor
    0.69
     priced
    0.68
     aligned
    0.68
     sized
    0.68
    Act Density 0.014%

    No Known Activations