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

    Neuronpedia

    INDEX
    Explanations

    numerals and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to sections or parts of a text or website

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nt
    -0.54
     ruining
    -0.53
     worthless
    -0.52
     didnt
    -0.51
     violation
    -0.50
     rubbish
    -0.50
     rejection
    -0.50
     wont
    -0.48
     useless
    -0.48
     faults
    -0.48
    POSITIVE LOGITS
    alan
    0.62
    姫
    0.59
    luster
    0.59
    arger
    0.55
    lique
    0.55
    ular
    0.53
    reditary
    0.52
    pherd
    0.50
    atown
    0.49
    ordial
    0.49
    Act Density 0.692%

    No Known Activations