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

    Neuronpedia

    INDEX
    Explanations

    well-written and informative blog content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALA
    -0.15
    би
    -0.15
    647
    -0.15
    asher
    -0.15
    ophy
    -0.15
     nø
    -0.14
    mÃŃ
    -0.14
    ASH
    -0.14
    ادÙĩ
    -0.13
    ضÙĬ
    -0.13
    POSITIVE LOGITS
    ungan
    0.16
     pers
    0.15
     flag
    0.15
     p
    0.15
     Flag
    0.14
     Cabr
    0.14
    alia
    0.13
    ahlen
    0.13
    дав
    0.13
     Mang
    0.13
    Act Density 0.008%

    No Known Activations