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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules and regulations

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols related to division or separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scrib
    -0.81
     Shooter
    -0.73
     tabl
    -0.68
     Creep
    -0.67
     Eid
    -0.65
     Roof
    -0.65
     Strat
    -0.65
     Cats
    -0.63
     Manson
    -0.62
     Congo
    -0.62
    POSITIVE LOGITS
    say
    0.94
    ad
    0.88
    leg
    0.87
    via
    0.83
    adv
    0.82
    devices
    0.80
    maybe
    0.79
    sole
    0.79
    etc
    0.79
    hid
    0.78
    Act Density 0.016%

    No Known Activations