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

    Neuronpedia

    INDEX
    Explanations

    references to authoritative figures and political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esis
    -0.15
     Ross
    -0.14
    айд
    -0.14
    ãĥ³ãĥĩãĤ£
    -0.14
    raf
    -0.14
     Kumar
    -0.14
    af
    -0.13
     aktu
    -0.13
     Slug
    -0.13
     passions
    -0.13
    POSITIVE LOGITS
    encent
    0.19
    iten
    0.16
    usk
    0.15
     Parliamentary
    0.15
    loyment
    0.15
    helm
    0.14
    Scheme
    0.13
    ба
    0.13
     Shepard
    0.13
    å§Ĩ
    0.13
    Act Density 0.018%

    No Known Activations