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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -0.61
     CWE
    -0.56
    )(((
    -0.52
     quæ
    -0.52
     représ
    -0.52
    disfraz
    -0.51
    theoremstyle
    -0.51
    orsese
    -0.50
     Савезне
    -0.50
    wiſe
    -0.49
    POSITIVE LOGITS
     rồi
    0.60
     Вікі
    0.60
     apologe
    0.59
    Przypisy
    0.58
     hurriedly
    0.56
     glances
    0.55
     Затем
    0.55
    DECREF
    0.53
    ագրություններ
    0.53
    ValueStyle
    0.53
    Act Density 0.307%

    No Known Activations