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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases that seek clarification or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.75
    Them
    -0.66
    HtmlAttribute
    -0.65
    Geografi
    -0.65
    Datuak
    -0.64
     Inscrivez
    -0.63
     honom
    -0.62
     Descrip
    -0.61
     său
    -0.61
    Jangan
    -0.61
    POSITIVE LOGITS
     they
    1.72
     we
    1.23
     it
    1.21
     these
    1.06
     he
    1.06
     the
    1.03
     those
    1.03
     you
    0.95
     each
    0.95
     she
    0.91
    Act Density 0.215%

    No Known Activations