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

    Neuronpedia

    INDEX
    Explanations

    phrases that include quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fulton
    -0.14
    alach
    -0.13
    aida
    -0.13
    ipes
    -0.13
     tire
    -0.13
    ture
    -0.13
    âm
    -0.13
    /renderer
    -0.13
     sina
    -0.13
     fu
    -0.13
    POSITIVE LOGITS
     Eck
    0.15
    iaux
    0.15
    uld
    0.15
    ķĮ
    0.15
    ieber
    0.14
    nech
    0.14
    construct
    0.14
     تخ
    0.14
    jabi
    0.14
    ULD
    0.13
    Act Density 0.001%

    No Known Activations