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

    Neuronpedia

    INDEX
    Explanations

    capitalized letters at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    the letter "A" or instances that contain the letter "A"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oswald
    -0.64
    anism
    -0.62
     proceedings
    -0.61
    olicy
    -0.61
    },{"
    -0.61
     Orient
    -0.60
     Abortion
    -0.59
     Adin
    -0.58
    pees
    -0.57
    Finish
    -0.57
    POSITIVE LOGITS
    cknowled
    1.50
    cknow
    1.36
    HAHAHAHA
    1.18
    HAHA
    1.13
    HHHH
    1.11
    ctors
    1.04
    chieve
    1.02
    verages
    1.00
     lot
    1.00
    lyss
    1.00
    Act Density 0.174%

    No Known Activations