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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating actions or processes, particularly in the context of making decisions or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹Ģà¸Ĺ
    -0.15
    aversable
    -0.14
    аном
    -0.14
    nÄĽjÅ¡ÃŃ
    -0.13
    ORB
    -0.13
    ÃŃÅĻ
    -0.13
    eniable
    -0.13
    rias
    -0.13
    ırken
    -0.12
    eÄį
    -0.12
    POSITIVE LOGITS
     just
    1.06
    just
    0.93
     Just
    0.89
    Just
    0.88
     JUST
    0.82
     juste
    0.71
    .just
    0.70
    å°±
    0.62
    JUST
    0.61
    "Just
    0.59
    Act Density 0.335%

    No Known Activations