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

    Neuronpedia

    INDEX
    Explanations

    connections or associations between various factors or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to associations or connections between different subjects or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.71
    sburg
    -0.70
    stall
    -0.67
    perty
    -0.67
     Penguins
    -0.66
     Sev
    -0.66
    otos
    -0.64
    æµ
    -0.63
     Pens
    -0.61
    kay
    -0.60
    POSITIVE LOGITS
    edin
    0.91
    linked
    0.89
     knot
    0.78
     dots
    0.76
    link
    0.74
     links
    0.73
     disparate
    0.72
     linking
    0.70
    chain
    0.70
     linked
    0.68
    Act Density 0.030%

    No Known Activations