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

    Neuronpedia

    INDEX
    Explanations

    words related to geometric shapes, particularly those ending in 'el' and 'ob'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "obstacle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.67
    pring
    -0.65
     pods
    -0.64
    iffin
    -0.59
    bnb
    -0.56
    earch
    -0.56
    ère
    -0.56
     accelerator
    -0.56
    isSpecialOrderable
    -0.55
     McMaster
    -0.55
    POSITIVE LOGITS
    uary
    0.90
    ption
    0.79
    merce
    0.70
    acles
    0.67
    Wan
    0.66
    uct
    0.66
    gyn
    0.66
    iqueness
    0.65
    itely
    0.62
    fusc
    0.61
    Act Density 0.132%

    No Known Activations