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

    Neuronpedia

    INDEX
    Explanations

    terms related to documentation, reporting, and the organization of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tÃŃn
    -0.16
    ÑĤап
    -0.16
    antan
    -0.15
    sek
    -0.15
    mites
    -0.14
    ISM
    -0.14
    erse
    -0.14
    lla
    -0.14
     decay
    -0.14
    icol
    -0.14
    POSITIVE LOGITS
    ory
    0.50
    ary
    0.50
    ories
    0.42
    ORY
    0.41
    aries
    0.37
    ARY
    0.36
    atory
    0.36
    orial
    0.35
    orio
    0.34
    orry
    0.33
    Act Density 0.056%

    No Known Activations