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

    Neuronpedia

    INDEX
    Explanations

    general statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilib
    -0.15
    ghan
    -0.15
     sometimes
    -0.14
     potentially
    -0.14
     possibly
    -0.14
    ugh
    -0.14
     æĪ
    -0.13
    ãģŁãĤĬ
    -0.13
    lap
    -0.13
     Keywords
    -0.13
    POSITIVE LOGITS
     speaking
    0.24
    -speaking
    0.23
     generally
    0.21
     Generally
    0.20
    Generally
    0.19
    à¹ģล
    0.17
    üstü
    0.17
    EMS
    0.16
     general
    0.15
    izon
    0.15
    Act Density 0.044%

    No Known Activations