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

    Neuronpedia

    INDEX
    Explanations

    short phrases indicating a specific duration of time

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that convey a sense of brevity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.82
    enne
    -0.76
    ynthesis
    -0.76
    someone
    -0.74
    eteria
    -0.73
    ylum
    -0.72
    uddin
    -0.70
    affer
    -0.69
    isine
    -0.69
     Cros
    -0.68
    POSITIVE LOGITS
     thirds
    0.97
     paragraphs
    0.91
     districts
    0.85
     categories
    0.84
     ounces
    0.84
     halves
    0.81
     pairs
    0.80
     TDs
    0.79
     slots
    0.79
     counties
    0.79
    Act Density 0.265%

    No Known Activations