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

    Neuronpedia

    INDEX
    Explanations

    verbs or verb phrases related to performing actions or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     €€
    -0.73
    sizePolicy
    -0.65
    Zgod
    -0.61
    cassert
    -0.61
    fcntl
    -0.60
     pymysql
    -0.57
     smtplib
    -0.57
    Въ
    -0.56
    stdarg
    -0.55
     hashlib
    -0.54
    POSITIVE LOGITS
     intersper
    1.08
     uninten
    0.96
     shenan
    0.92
     maneu
    0.92
     Here
    0.88
    Here
    0.85
     affor
    0.85
     scrat
    0.83
     increa
    0.83
     fortn
    0.83
    Act Density 0.055%

    No Known Activations