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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases or keywords that are significant or noteworthy

    oai_token-act-pair · gpt-3.5-turbo

    references to key details or important bits of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esi
    -0.76
    oped
    -0.74
    ©¶æ
    -0.73
    raid
    -0.67
    opa
    -0.67
    sole
    -0.65
    enne
    -0.61
    aline
    -0.61
    oping
    -0.58
    gger
    -0.58
    POSITIVE LOGITS
    stroke
    0.90
     imaginable
    0.89
     aspects
    0.78
     details
    0.78
     pertaining
    0.76
     viz
    0.75
     detail
    0.70
     wrinkles
    0.70
     specifics
    0.69
     touches
    0.67
    Act Density 0.369%

    No Known Activations