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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "some" and its varying contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪов
    -0.15
    inely
    -0.15
    -wise
    -0.15
    dou
    -0.14
    eway
    -0.14
    /repository
    -0.14
    ÑĢобÑĸÑĤ
    -0.14
    arily
    -0.13
    .Sdk
    -0.13
    incy
    -0.13
    POSITIVE LOGITS
     purposes
    0.45
     reason
    0.42
     sake
    0.39
     reasons
    0.37
    reason
    0.33
    Reason
    0.27
     intents
    0.27
     purpose
    0.25
     Reason
    0.24
    .reason
    0.23
    Act Density 0.059%

    No Known Activations