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

    Neuronpedia

    INDEX
    Explanations

    programming-related terminology and data structure references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apiro
    -0.15
    xBB
    -0.15
    oad
    -0.15
    inite
    -0.14
    ĨĴ
    -0.14
    orra
    -0.14
    owl
    -0.14
    phabet
    -0.13
     Ao
    -0.13
    oins
    -0.13
    POSITIVE LOGITS
    ÏĨαÏģ
    0.15
    _REG
    0.14
    اØ
    0.14
    emoc
    0.14
    hei
    0.14
    ÅĻeh
    0.14
    strar
    0.14
     discrim
    0.14
    ustr
    0.14
    LOS
    0.14
    Act Density 0.005%

    No Known Activations