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

    Neuronpedia

    INDEX
    Explanations

    prepositions and words related to communication and response

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    audiovisuel
    -0.60
     peines
    -0.59
     dégust
    -0.58
    <bos>
    -0.57
     déclarations
    -0.56
     toscana
    -0.56
     gawas
    -0.55
     Améli
    -0.54
     boîtes
    -0.53
    ఔ
    -0.52
    POSITIVE LOGITS
     stimuli
    0.66
     requests
    0.54
     criticisms
    0.53
     stimulus
    0.51
     questions
    0.51
     criticism
    0.50
     challenges
    0.49
     suggestions
    0.48
     queries
    0.48
     threats
    0.48
    Act Density 0.165%

    No Known Activations