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

    Neuronpedia

    INDEX
    Explanations

    words related to unusual or abnormal situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noinspection
    -0.16
    bes
    -0.14
    inous
    -0.14
    ted
    -0.14
    thed
    -0.14
    imid
    -0.14
    mund
    -0.14
     mean
    -0.13
    andas
    -0.13
    isans
    -0.13
    POSITIVE LOGITS
    ities
    0.27
    -shaped
    0.23
    itics
    0.20
    ly
    0.20
    -looking
    0.19
    ball
    0.19
    ity
    0.19
    -ball
    0.19
     discrepan
    0.19
    iti
    0.18
    Act Density 0.063%

    No Known Activations