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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "other" and related phrases conveying additional information or examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esis
    -0.14
    Ł
    -0.14
    xp
    -0.14
    ling
    -0.14
    unction
    -0.14
    ociety
    -0.13
     OTHERWISE
    -0.13
    xs
    -0.13
     mirac
    -0.13
    ÑĤов
    -0.13
    POSITIVE LOGITS
    ewise
    0.20
    vely
    0.19
     similarly
    0.18
     Similarly
    0.15
    ardy
    0.15
    Similarly
    0.15
     equally
    0.14
    kili
    0.14
    edge
    0.14
    lik
    0.14
    Act Density 0.043%

    No Known Activations