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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "out" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quette
    -0.19
    Ùĩ
    -0.18
    holes
    -0.17
    cheng
    -0.17
    kins
    -0.16
    _output
    -0.16
    nul
    -0.16
    {{{
    -0.16
    ements
    -0.15
    OperationException
    -0.15
    POSITIVE LOGITS
    ta
    0.28
    wards
    0.27
    -of
    0.22
    land
    0.21
    ters
    0.21
    ting
    0.20
    last
    0.19
    lying
    0.19
    ted
    0.19
    sert
    0.19
    Act Density 0.191%

    No Known Activations