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

    Neuronpedia

    INDEX
    Explanations

    references to probabilities and the likelihood of events occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <dynamic
    -0.14
    oga
    -0.14
    esto
    -0.14
    elson
    -0.14
     nạn
    -0.13
    麦
    -0.13
     Taken
    -0.13
    Plug
    -0.13
    most
    -0.13
     taken
    -0.13
    POSITIVE LOGITS
     chance
    0.18
    çİĩ
    0.15
    leen
    0.15
    ikh
    0.14
    296
    0.14
    _updates
    0.14
     occurrence
    0.13
    hood
    0.13
    bere
    0.13
     tw
    0.13
    Act Density 0.059%

    No Known Activations