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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detection and monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.21
    agi
    -0.16
    ellido
    -0.16
    pered
    -0.16
    âĸłâĸł
    -0.15
    esterday
    -0.15
    ipp
    -0.15
    elves
    -0.14
    IPP
    -0.14
    elve
    -0.14
    POSITIVE LOGITS
    iveness
    0.17
    nis
    0.16
    ives
    0.16
    /count
    0.16
    μί
    0.15
    660
    0.15
    ernes
    0.14
    ively
    0.14
    949
    0.14
    ad
    0.14
    Act Density 0.024%

    No Known Activations