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

    Neuronpedia

    INDEX
    Explanations

    references to external or outside elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hole
    -0.19
     outstanding
    -0.18
    holes
    -0.17
    ãĥ¼ãĥĪ
    -0.17
     Outstanding
    -0.16
    eda
    -0.16
    _output
    -0.15
    /output
    -0.15
     (;;)
    -0.15
    outing
    -0.15
    POSITIVE LOGITS
    /internal
    0.31
    /Internal
    0.23
    /in
    0.19
    wear
    0.18
    -facing
    0.17
    enan
    0.17
    uber
    0.16
     chance
    0.16
     Chance
    0.16
     circumstances
    0.15
    Act Density 0.038%

    No Known Activations