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

    Neuronpedia

    INDEX
    Explanations

    numerical averages in points and rebounds in a sports context

    oai_token-act-pair · gpt-3.5-turbo

    decimal numbers and their related statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     handshake
    -0.63
     advis
    -0.63
     asylum
    -0.58
    ļéĨĴ
    -0.58
     cyclist
    -0.57
     shake
    -0.56
     welfare
    -0.56
     gad
    -0.55
     swim
    -0.55
     PTS
    -0.55
    POSITIVE LOGITS
    0
    1.07
    5
    1.04
    8
    1.02
    9
    1.01
    6
    0.99
    7
    0.95
    50
    0.95
    38
    0.92
    53
    0.92
    3
    0.91
    Act Density 0.128%

    No Known Activations