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

    Neuronpedia

    INDEX
    Explanations

    the presence of code-like structures or commands in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the start of a new document/section and references to invited participants or guest appearances (like “guest stars” or event speakers).

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Negative Logits
     Whittaker
    -0.69
    tened
    -0.65
    mtd
    -0.64
     Str
    -0.63
    thâu
    -0.62
     Strickland
    -0.62
     ols
    -0.62
    IComponent
    -0.61
    ioid
    -0.60
    ysteem
    -0.60
    POSITIVE LOGITS
     GUEST
    1.70
     guest
    1.68
     guests
    1.63
     Guests
    1.59
    GUEST
    1.59
     Guest
    1.57
    Guest
    1.46
    Guests
    1.45
    guest
    1.41
    guests
    1.38
    Act Density 0.103%

    No Known Activations