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

    Neuronpedia

    INDEX
    Explanations

    segments related to comments, opinions, or discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illance
    -0.20
    estro
    -0.16
    .PropTypes
    -0.16
    803
    -0.15
    ault
    -0.15
    746
    -0.14
    ium
    -0.14
    eldon
    -0.14
    APS
    -0.14
    owns
    -0.14
    POSITIVE LOGITS
    æĽ²
    0.15
    mere
    0.15
    alen
    0.14
     Bab
    0.14
    ola
    0.14
    çIJ´
    0.13
    eba
    0.13
    OLA
    0.13
    etus
    0.13
    alo
    0.13
    Act Density 0.157%

    No Known Activations