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

    Neuronpedia

    INDEX
    Explanations

    various forms and discussions of arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orian
    -0.16
    emain
    -0.15
    диÑı
    -0.15
    pst
    -0.14
    zk
    -0.14
    igkeit
    -0.14
    gne
    -0.14
    vor
    -0.14
    anner
    -0.14
     sert
    -0.14
    POSITIVE LOGITS
    atively
    0.18
    ative
    0.18
     arguments
    0.17
     argument
    0.16
    =args
    0.16
    ados
    0.16
     Argument
    0.15
     Arguments
    0.15
    linger
    0.15
     args
    0.14
    Act Density 0.025%

    No Known Activations