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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news coverage and discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chop
    -0.15
    éĵ
    -0.15
    коÑĤ
    -0.14
     ÑģоÑģÑĤав
    -0.14
    adera
    -0.14
    çĥŁ
    -0.14
    ALCHEMY
    -0.13
    ypo
    -0.13
    enza
    -0.13
     nackte
    -0.13
    POSITIVE LOGITS
    λαν
    0.17
    /raw
    0.14
    velt
    0.14
    eum
    0.13
    åķĨ
    0.13
    raz
    0.13
    ansom
    0.13
     ""
    0.13
     batches
    0.13
     tang
    0.13
    Act Density 0.055%

    No Known Activations