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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a transition or contrast in concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ond
    -0.17
    wick
    -0.15
    åł±
    -0.15
    вание
    -0.15
    abi
    -0.14
    avad
    -0.14
     ÑģилÑĥ
    -0.14
     Closure
    -0.14
    abase
    -0.14
     Either
    -0.14
    POSITIVE LOGITS
     Seg
    0.15
    rech
    0.14
    ensely
    0.14
    ieder
    0.14
     Tup
    0.14
    istrovstvÃŃ
    0.14
    antium
    0.14
    gebra
    0.14
    ayne
    0.14
    ESH
    0.13
    Act Density 0.055%

    No Known Activations