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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wunused
    -0.16
    ECH
    -0.16
    ault
    -0.16
    ве
    -0.15
    ings
    -0.15
    igne
    -0.14
    _Right
    -0.14
    bob
    -0.14
    anne
    -0.14
    athers
    -0.14
    POSITIVE LOGITS
    BERS
    0.26
    éro
    0.23
    bers
    0.23
    eral
    0.23
    ismatic
    0.23
    erals
    0.21
    ercial
    0.19
    érique
    0.19
    UpDown
    0.19
    ICAL
    0.18
    Act Density 0.012%

    No Known Activations