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

    Neuronpedia

    INDEX
    Explanations

    dates and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.63
     appre
    -0.63
    heter
    -0.62
    lycer
    -0.61
    ecast
    -0.60
    ccording
    -0.59
    antom
    -0.59
     reconc
    -0.58
     sensit
    -0.57
     resil
    -0.57
    POSITIVE LOGITS
     9
    0.87
     11
    0.85
     Submit
    0.83
     7
    0.81
     âĨij
    0.80
     09
    0.80
     8
    0.80
     2024
    0.78
     02
    0.76
     17
    0.76
    Act Density 0.141%

    No Known Activations