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

    Neuronpedia

    INDEX
    Explanations

    negations or exceptions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /antlr
    -0.17
    asher
    -0.17
    æĬ
    -0.14
     rtl
    -0.14
     Rent
    -0.14
    uxt
    -0.14
    aru
    -0.14
    ijd
    -0.14
    ACY
    -0.14
    UNET
    -0.14
    POSITIVE LOGITS
     rods
    0.27
     rod
    0.20
    _COLL
    0.20
    coll
    0.19
     rule
    0.18
     Coll
    0.17
     Rod
    0.17
     COLL
    0.17
    /rc
    0.17
     coll
    0.17
    Act Density 0.000%

    No Known Activations