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

    Neuronpedia

    INDEX
    Explanations

    themes related to abstract concepts and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URITY
    -0.19
     addCriterion
    -0.17
    groupon
    -0.16
     célib
    -0.15
    ÑģÑĤи
    -0.15
    लत
    -0.15
    onto
    -0.15
    lopedia
    -0.15
    ouncer
    -0.15
    riad
    -0.14
    POSITIVE LOGITS
     enough
    0.25
     territory
    0.25
     wise
    0.23
    wise
    0.23
    ier
    0.22
     adjacent
    0.21
    ly
    0.20
     dependent
    0.20
     orient
    0.20
    ish
    0.20
    Act Density 0.196%

    No Known Activations