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

    Neuronpedia

    INDEX
    Explanations

    phrases or conjunctions that suggest conditional or contrasting relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #ad
    -0.17
    ify
    -0.15
    ılı
    -0.15
    kick
    -0.14
    stub
    -0.14
    Ìģt
    -0.14
    utar
    -0.14
    Å¡ky
    -0.14
     nackte
    -0.13
    _COMPAT
    -0.13
    POSITIVE LOGITS
     wed
    0.13
    yna
    0.13
    yen
    0.12
    braska
    0.12
     im
    0.12
     superv
    0.12
    151
    0.12
     z
    0.11
    ī
    0.11
    159
    0.11
    Act Density 0.130%

    No Known Activations