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

    Neuronpedia

    INDEX
    Explanations

    keywords relating to operational or procedural elements in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ris
    -0.20
    hra
    -0.18
    rv
    -0.18
    NO
    -0.17
    kes
    -0.17
    pas
    -0.17
    pers
    -0.17
    nt
    -0.17
    rt
    -0.16
    b
    -0.16
    POSITIVE LOGITS
    vertime
    0.22
    'clock
    0.21
    ehler
    0.21
    etting
    0.20
    verture
    0.20
    phthalm
    0.19
    lymp
    0.19
    ceans
    0.19
    aths
    0.19
    ates
    0.18
    Act Density 0.066%

    No Known Activations