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

    Neuronpedia

    INDEX
    Explanations

    specific numbers or references in a structured format within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 13

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.88
    ierrez
    -0.78
     tradem
    -0.73
    anamo
    -0.71
    ifully
    -0.68
    gart
    -0.68
     belly
    -0.62
    iques
    -0.62
    HAHAHAHA
    -0.61
    razil
    -0.61
    POSITIVE LOGITS
    66
    0.98
    rd
    0.94
    37
    0.92
     Reasons
    0.88
    87
    0.88
    94
    0.86
    76
    0.86
    97
    0.84
    63
    0.83
    33
    0.83
    Act Density 0.030%

    No Known Activations