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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format in the text

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.73
    GGGGGGGG
    -0.60
    Marginal
    -0.59
    BIL
    -0.58
     styl
    -0.58
     showc
    -0.56
    bda
    -0.55
    illas
    -0.54
     animals
    -0.53
     SPACE
    -0.53
    POSITIVE LOGITS
    ulhu
    1.02
    ioxide
    1.00
    endment
    0.87
    icum
    0.81
    ousand
    0.80
     Amendment
    0.79
    umbnail
    0.79
     onwards
    0.78
     Harbor
    0.77
    rum
    0.77
    Act Density 0.021%

    No Known Activations