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

    Neuronpedia

    INDEX
    Explanations

    phrases related to announcements, updates, and releases

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or releases by a group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.80
     harms
    -0.70
    ['
    -0.67
    imum
    -0.65
     worldview
    -0.65
    SpaceEngineers
    -0.62
    PLA
    -0.61
     Bundy
    -0.61
    soever
    -0.60
     manipulative
    -0.60
    POSITIVE LOGITS
     reprint
    0.91
     teamed
    0.91
     revisit
    0.90
     publish
    0.88
     roundup
    0.87
     introduce
    0.85
    blogs
    0.84
    Introdu
    0.84
     NEWS
    0.83
     previews
    0.83
    Act Density 0.248%

    No Known Activations