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

    Neuronpedia

    INDEX
    Explanations

    statements about improvement or success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isas
    -0.17
    bject
    -0.15
    LocalizedString
    -0.15
    ongan
    -0.15
    itrust
    -0.14
    554
    -0.14
    tha
    -0.14
    olls
    -0.14
    291
    -0.14
    wan
    -0.14
    POSITIVE LOGITS
     happen
    0.35
     available
    0.25
     possible
    0.24
     noises
    0.20
     known
    0.20
     count
    0.19
     Stick
    0.19
     Possible
    0.19
     happens
    0.19
     Known
    0.19
    Act Density 0.094%

    No Known Activations