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

    Neuronpedia

    INDEX
    Explanations

    declarations of classes and methods within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bowen
    -0.15
    öst
    -0.15
    onom
    -0.15
     ظ
    -0.14
    chin
    -0.14
    yan
    -0.14
     fertil
    -0.14
    æĸĩçĮ®
    -0.14
    gili
    -0.14
    entifier
    -0.14
    POSITIVE LOGITS
    upo
    0.16
    vek
    0.16
    ampus
    0.15
    epad
    0.15
    rew
    0.15
    Ĥ¬
    0.14
    abin
    0.14
     standards
    0.13
     Standards
    0.13
    czy
    0.13
    Act Density 0.011%

    No Known Activations