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

    Neuronpedia

    INDEX
    Explanations

    terms related to health and safety regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erner
    -0.16
     Angela
    -0.14
     ideally
    -0.14
     topped
    -0.14
     dis
    -0.14
    hel
    -0.14
     uns
    -0.13
     Low
    -0.13
     area
    -0.13
    ser
    -0.13
    POSITIVE LOGITS
    ubu
    0.16
    ÑģÑĤе
    0.16
    illard
    0.15
    NotNil
    0.15
    øre
    0.15
    ilig
    0.15
    IDO
    0.14
    inance
    0.14
     widely
    0.14
    ALSE
    0.14
    Act Density 0.163%

    No Known Activations