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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation and explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    αÏģά
    -0.17
    Appointment
    -0.16
     Appointment
    -0.15
    istrovstvÃŃ
    -0.15
    onymous
    -0.14
    ูà¹Ī
    -0.14
     Anonymous
    -0.14
     cái
    -0.14
    .Raise
    -0.14
    rong
    -0.14
    POSITIVE LOGITS
    MT
    0.17
     Magn
    0.15
    ãĤ¹ãĤ¿ãĥ¼
    0.15
     sched
    0.14
     magn
    0.14
    504
    0.13
    zza
    0.13
     Wal
    0.13
     Scene
    0.13
     ucwords
    0.13
    Act Density 0.609%

    No Known Activations