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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .setProgress
    -0.15
    UILTIN
    -0.15
    ione
    -0.14
    ÅĻ
    -0.14
    eck
    -0.14
    gem
    -0.14
    SSION
    -0.14
    agi
    -0.13
     moo
    -0.13
     Baum
    -0.13
    POSITIVE LOGITS
    kea
    0.15
    usher
    0.14
     co
    0.14
    iyon
    0.14
     Bid
    0.14
    cket
    0.14
    INGER
    0.14
    oldt
    0.14
    751
    0.13
     dow
    0.13
    Act Density 0.054%

    No Known Activations