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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    text formatted like timestamps or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Origin
    -0.70
     grop
    -0.70
     gorilla
    -0.69
     usher
    -0.68
    ļéĨĴ
    -0.66
     mature
    -0.65
     chop
    -0.65
     lineage
    -0.64
     basket
    -0.63
     Dragonbound
    -0.63
    POSITIVE LOGITS
    2012
    1.21
    2014
    1.21
    2013
    1.20
    2015
    1.18
    09
    1.17
    2017
    1.16
    08
    1.14
    11
    1.14
    2010
    1.13
    12
    1.13
    Act Density 0.026%

    No Known Activations