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

    Neuronpedia

    INDEX
    Explanations

    unrelated events or items mentioned within the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of relevance or connection to the main topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oise
    -0.73
    ocker
    -0.71
    aeper
    -0.71
    amping
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    addafi
    -0.69
    ifter
    -0.68
    âķIJâķIJ
    -0.67
    asure
    -0.66
    aneers
    -0.65
    POSITIVE LOGITS
     unrelated
    1.11
     minded
    0.90
    worldly
    0.88
     thereto
    0.88
    ities
    0.77
    minded
    0.77
    nesses
    0.76
    TextColor
    0.76
    wise
    0.75
    hetical
    0.74
    Act Density 0.008%

    No Known Activations