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

    Neuronpedia

    INDEX
    Explanations

    objects or tools that can be held or used to interact with physical objects

    oai_token-act-pair · gpt-3.5-turbo

    physical objects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EGIN
    -0.80
     VIDEOS
    -0.73
     demographics
    -0.72
     mortals
    -0.72
     incumb
    -0.70
     arenas
    -0.69
     venues
    -0.69
     partnerships
    -0.69
     Events
    -0.68
     timelines
    -0.68
    POSITIVE LOGITS
    pipe
    1.07
     shaped
    0.98
    hole
    0.98
    brush
    0.98
    fish
    0.92
    hook
    0.92
    icum
    0.87
    cloth
    0.87
    pee
    0.87
    bar
    0.87
    Act Density 0.287%

    No Known Activations