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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ¦
    -0.16
    ÑĢоÑĪ
    -0.15
    azers
    -0.14
    ient
    -0.14
    aler
    -0.14
    swer
    -0.14
    emp
    -0.13
    alc
    -0.13
    agna
    -0.13
    steller
    -0.13
    POSITIVE LOGITS
    asad
    0.15
    roys
    0.15
    drawing
    0.14
    IRD
    0.14
    okers
    0.13
    å§Ĩ
    0.13
    load
    0.13
    oker
    0.13
    æĪ
    0.13
    ilda
    0.13
    Act Density 0.001%

    No Known Activations