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

    Neuronpedia

    INDEX
    Explanations

    the word "can" and its variations, indicating potential or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amel
    -0.17
    .Butter
    -0.15
    abi
    -0.15
    -transitional
    -0.15
    adr
    -0.15
    amient
    -0.14
    UTE
    -0.14
    apol
    -0.14
    ahren
    -0.14
    elist
    -0.14
    POSITIVE LOGITS
     able
    0.20
     anytime
    0.15
    伯
    0.15
    죽
    0.15
    opus
    0.15
    anime
    0.14
     possibility
    0.14
    753
    0.14
     Able
    0.14
    lon
    0.14
    Act Density 0.143%

    No Known Activations