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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific dates or instructions

    oai_token-act-pair · gpt-3.5-turbo

    words related to sleep, celebrations, and actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.57
    .[
    -0.56
    ,—
    -0.56
    ;
    -0.55
    ,[
    -0.55
    ,
    -0.52
    .—
    -0.52
     Micha
    -0.51
    :
    -0.51
     Senator
    -0.49
    POSITIVE LOGITS
    externalActionCode
    0.68
    ãĤ´ãĥ³
    0.68
    leep
    0.64
    Browser
    0.60
    âķIJâķIJ
    0.58
    ctive
    0.56
    ãĥİ
    0.54
    EStreamFrame
    0.54
    STD
    0.53
    WithNo
    0.53
    Act Density 1.218%

    No Known Activations