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

    Neuronpedia

    INDEX
    Explanations

    strings of numbers separated by slashes

    oai_token-act-pair · gpt-3.5-turbo

    elements related to numerical data or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.91
     DRAG
    -0.72
    ÃŃs
    -0.68
     successors
    -0.66
     secretaries
    -0.66
     deputies
    -0.60
     outward
    -0.60
     handheld
    -0.59
     Sisters
    -0.59
    ¨
    -0.59
    POSITIVE LOGITS
    014
    1.23
    585
    1.16
    802
    1.15
    806
    1.15
    646
    1.14
    995
    1.14
    698
    1.13
    394
    1.13
    648
    1.13
    294
    1.11
    Act Density 0.064%

    No Known Activations