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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.15
     sund
    -0.15
    igne
    -0.15
    ugo
    -0.14
     Bucc
    -0.13
    ittest
    -0.13
    /Peak
    -0.13
    ovo
    -0.13
    andin
    -0.13
     kans
    -0.13
    POSITIVE LOGITS
     list
    0.19
     number
    0.17
     amount
    0.17
     portion
    0.16
    retty
    0.15
    umber
    0.15
    amount
    0.15
     range
    0.15
     set
    0.14
    Ctrls
    0.14
    Act Density 0.166%

    No Known Activations