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

    Neuronpedia

    INDEX
    Explanations

    code-related strings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of hashtags, likely indicating social media or coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.84
     satell
    -0.80
     minded
    -0.79
    issance
    -0.78
     oun
    -0.78
    emouth
    -0.76
    cellence
    -0.74
    chwitz
    -0.73
     contemplation
    -0.71
    ciation
    -0.70
    POSITIVE LOGITS
    ################################
    1.37
    ########
    1.32
    ################
    1.22
    DIV
    1.21
    ERROR
    1.14
    define
    1.12
    ###
    1.09
     ##
    0.93
    NAME
    0.91
    REF
    0.91
    Act Density 0.016%

    No Known Activations