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

    Neuronpedia

    INDEX
    Explanations

    literal string representations or constructor calls in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acher
    -0.16
    ãĤ¤ãĥī
    -0.15
    iza
    -0.15
    anghai
    -0.14
     Greenwood
    -0.14
     neutr
    -0.13
    plen
    -0.13
    Tw
    -0.13
    avan
    -0.13
    ervals
    -0.13
    POSITIVE LOGITS
    ajas
    0.23
    atron
    0.15
    ardu
    0.15
    EFAULT
    0.15
     scratch
    0.14
    inton
    0.14
    atonin
    0.14
    tÃŃ
    0.13
    swana
    0.13
    /is
    0.13
    Act Density 0.030%

    No Known Activations