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

    Neuronpedia

    INDEX
    Explanations

    references to specific upcoming events, announcements, and schedules

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a reference or source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.87
    odox
    -0.80
    ngth
    -0.78
     exting
    -0.75
    ilial
    -0.71
    aith
    -0.67
    tein
    -0.66
    acl
    -0.66
    oubted
    -0.65
    ouver
    -0.64
    POSITIVE LOGITS
     Kaepernick
    0.62
     Hearthstone
    0.60
     offseason
    0.56
     NFL
    0.53
     NASCAR
    0.53
     NBA
    0.53
     DeVos
    0.52
     NCAA
    0.52
     Airbnb
    0.52
     postseason
    0.52
    Act Density 2.350%

    No Known Activations