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

    Neuronpedia

    INDEX
    Explanations

    markers indicating document structure or significant transitions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !!!!!!
    -0.59
     cds
    -0.58
    !!!!!!!
    -0.58
    ❣️
    -0.57
     merveilleux
    -0.57
    !!!!!!!!!!
    -0.57
    !!!!!
    -0.56
    !!!!!!!!
    -0.55
     دیکھیے
    -0.55
     vardır
    -0.55
    POSITIVE LOGITS
    ̵
    0.79
     via
    0.77
    RenderAtEndOf
    0.74
     albeit
    0.74
    via
    0.72
    Elsewhere
    0.71
    новништво
    0.71
    Via
    0.70
     folks
    0.70
     pretty
    0.70
    Act Density 0.427%

    No Known Activations