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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing possibility and conjecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $MESS
    -0.17
    è±
    -0.17
    à¹Īาย
    -0.15
    uitka
    -0.15
    .ServiceModel
    -0.15
    aint
    -0.15
    ç·¨
    -0.15
    FromArray
    -0.14
    anel
    -0.14
    ANEL
    -0.14
    POSITIVE LOGITS
     ast
    0.24
     aa
    0.23
     us
    0.21
    ast
    0.19
     ns
    0.18
    as
    0.18
     ass
    0.17
    ás
    0.17
    ास
    0.16
     ad
    0.16
    Act Density 0.073%

    No Known Activations