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

    Neuronpedia

    INDEX
    Explanations

    updates or news mentions in a text

    oai_token-act-pair · gpt-3.5-turbo

    information updates or announcements related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aden
    -0.84
    athered
    -0.83
    stood
    -0.77
    anyon
    -0.76
    anship
    -0.74
    gravity
    -0.73
    ographically
    -0.72
    ographies
    -0.71
    uman
    -0.69
     sheltered
    -0.68
    POSITIVE LOGITS
     Update
    1.04
    Update
    0.99
    UPDATE
    0.96
     UPDATE
    0.96
    :
    0.91
    !:
    0.89
    :]
    0.89
     EDIT
    0.86
     Sources
    0.84
    endum
    0.83
    Act Density 0.031%

    No Known Activations