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

    Neuronpedia

    INDEX
    Explanations

    expressions of mutual support and connection between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.20
    _OTHER
    -0.17
    ug
    -0.16
    etur
    -0.16
     together
    -0.16
     zusammen
    -0.14
     otherwise
    -0.14
    arn
    -0.14
    furt
    -0.14
    ablo
    -0.14
    POSITIVE LOGITS
    hood
    0.20
     nhau
    0.17
    /us
    0.16
    elves
    0.15
    -même
    0.15
    ieron
    0.14
    /all
    0.14
     mutually
    0.14
    's
    0.14
     across
    0.14
    Act Density 0.019%

    No Known Activations