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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating service awards or recognitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uat
    -0.17
    åŀĤ
    -0.15
    ipay
    -0.15
    ernote
    -0.14
    284
    -0.14
     karÅŁÄ±
    -0.14
    ColumnInfo
    -0.14
    hoff
    -0.13
    ocoa
    -0.13
     conven
    -0.13
    POSITIVE LOGITS
     Shaft
    0.16
    ç«
    0.15
    olini
    0.15
    ngen
    0.15
    Dup
    0.14
     veter
    0.14
    SKTOP
    0.14
    inis
    0.14
    >Main
    0.14
    BITS
    0.13
    Act Density 0.005%

    No Known Activations