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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures of capability or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ائÙħ
    -0.16
     Fry
    -0.15
    ushi
    -0.15
    omi
    -0.15
    alice
    -0.14
    amel
    -0.14
     Barcl
    -0.14
    ppard
    -0.14
    ames
    -0.14
    ps
    -0.14
    POSITIVE LOGITS
    ãĥĪãĥ«
    0.16
    Rated
    0.15
     Comfort
    0.15
     Borg
    0.15
    539
    0.14
    /pm
    0.14
    dsn
    0.14
    ghan
    0.14
    imenti
    0.14
    styled
    0.14
    Act Density 0.007%

    No Known Activations