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

    Neuronpedia

    INDEX
    Explanations

    references to diversity and different types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.20
    ì°©
    -0.18
    /player
    -0.18
     Fraser
    -0.17
    eding
    -0.16
    .nz
    -0.15
    gers
    -0.15
    chy
    -0.15
    ỳ
    -0.15
    çĦ¶
    -0.14
    POSITIVE LOGITS
    iances
    0.19
    iations
    0.18
    /var
    0.17
    _dump
    0.17
    iability
    0.17
    ied
    0.17
    érique
    0.17
    degrees
    0.16
    nish
    0.16
    thur
    0.16
    Act Density 0.056%

    No Known Activations