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

    Neuronpedia

    INDEX
    Explanations

    elements related to safety and regulation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occo
    -0.17
    ansi
    -0.15
    öy
    -0.14
    ubes
    -0.14
    ilet
    -0.14
    dle
    -0.13
    εÏģο
    -0.13
     isize
    -0.13
    Toolkit
    -0.13
    аÑĢÑĩ
    -0.13
    POSITIVE LOGITS
     prior
    0.14
     inade
    0.14
    proper
    0.14
    ISCO
    0.14
    prior
    0.14
     hadn
    0.13
     knew
    0.13
    _TX
    0.13
    aily
    0.13
     experiment
    0.13
    Act Density 0.031%

    No Known Activations