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

    Neuronpedia

    INDEX
    Explanations

    terms related to highlighting or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieder
    -0.07
     lại
    -0.07
    pps
    -0.07
     how
    -0.06
    olls
    -0.06
    rani
    -0.06
    istr
    -0.06
    ialog
    -0.06
    quer
    -0.06
    isine
    -0.06
    POSITIVE LOGITS
    ers
    0.08
    edReader
    0.08
    nings
    0.08
    er
    0.08
    eting
    0.07
    edImage
    0.07
    ingly
    0.07
    enda
    0.07
    ering
    0.07
    ede
    0.07
    Act Density 0.006%

    No Known Activations