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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases starting with "whether."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esco
    -0.15
    GIN
    -0.14
    unte
    -0.14
    MBED
    -0.14
    hread
    -0.13
    icorn
    -0.13
    licative
    -0.13
    ÙģاÙĦ
    -0.13
    avis
    -0.13
    thur
    -0.13
    POSITIVE LOGITS
    stantiate
    0.14
    idders
    0.14
    674
    0.14
    aid
    0.14
    exion
    0.13
    λί
    0.13
    iky
    0.13
    è¿«
    0.13
    funcs
    0.13
    رÛĮÙĩ
    0.13
    Act Density 0.020%

    No Known Activations