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

    Neuronpedia

    INDEX
    Explanations

    the dot character followed by a sequence of numbers that represents a version

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purse
    -0.85
     striking
    -0.73
     framing
    -0.70
     preventive
    -0.68
    iru
    -0.68
     worsh
    -0.68
     affili
    -0.65
     ambul
    -0.65
     shutter
    -0.64
     gull
    -0.64
    POSITIVE LOGITS
    0
    1.23
    5
    1.14
    6
    1.02
    7
    1.01
    8
    0.99
    9
    0.97
    3
    0.97
    02
    0.97
    04
    0.97
    4
    0.96
    Act Density 0.059%

    No Known Activations