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

    Neuronpedia

    INDEX
    Explanations

    lines or sections of code that appear to follow a specific comment or formatting pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ================
    -0.75
    abetes
    -0.69
    b
    -0.67
    ​
    -0.62
    r
    -0.61
    e
    -0.60
    as
    -0.60
    er
    -0.59
    be
    -0.59
    is
    -0.58
    POSITIVE LOGITS
    ################
    1.45
    ##
    1.42
    ////////////////
    1.36
    ']))
    1.21
    ]")
    1.20
    ])):
    1.20
    #########
    1.18
    ########
    1.17
    ##############
    1.17
    ###########
    1.16
    Act Density 0.090%

    No Known Activations