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

    Neuronpedia

    INDEX
    Explanations

    mentions of changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative or significant changes being discussed or implemented

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographies
    -0.73
    agog
    -0.68
    ãĥ£
    -0.60
     DRAGON
    -0.60
    xious
    -0.57
    Phones
    -0.57
    amina
    -0.57
    ãĥ¥
    -0.56
    ILLE
    -0.56
     Americ
    -0.55
    POSITIVE LOGITS
    uits
    1.01
     wrought
    1.00
    ettings
    0.99
    hips
    0.90
     effected
    0.87
     instituted
    0.84
     thereto
    0.84
    hooting
    0.84
    hops
    0.82
    eatures
    0.81
    Act Density 0.095%

    No Known Activations