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

    Neuronpedia

    INDEX
    Explanations

    objects or items related to specific physical objects or settings, such as sheets, chips, carts, cans, chairs, sticks, flakes, bottles, brushes, receipts, animals, balls, dolls, masks, bombs, grenades, bars, torches, balloons

    oai_token-act-pair · gpt-3.5-turbo

    items associated with physical objects and tools

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬
    -0.82
    ãĥį
    -0.80
    AE
    -0.78
    Region
    -0.77
    Rate
    -0.75
     practition
    -0.75
    CLASS
    -0.75
    Services
    -0.71
    States
    -0.71
    Reviewer
    -0.70
    POSITIVE LOGITS
    hips
    1.33
    poons
    1.27
    mith
    1.18
    creen
    1.16
    uits
    1.09
    leeve
    1.07
    hift
    0.97
    poon
    0.96
    cale
    0.96
    pring
    0.92
    Act Density 0.312%

    No Known Activations