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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "add" and related terms, indicating a focus on adding or including elements or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cies
    -0.16
    ogl
    -0.15
    fulness
    -0.14
    ì²Ń
    -0.14
    acho
    -0.13
    еÑĢов
    -0.13
    udies
    -0.13
    gi
    -0.13
     Sting
    -0.13
    /Area
    -0.13
    POSITIVE LOGITS
    endum
    0.40
    -ons
    0.34
    ition
    0.33
    uce
    0.33
    resse
    0.32
    itionally
    0.29
    itive
    0.29
    icted
    0.28
    /sub
    0.28
    /remove
    0.27
    Act Density 0.080%

    No Known Activations