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

    Neuronpedia

    INDEX
    Explanations

    references to seat-related objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to seats in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.84
    issance
    -0.75
    operation
    -0.71
    icably
    -0.69
    cially
    -0.68
    istic
    -0.68
    ALLY
    -0.68
    ishly
    -0.66
    agascar
    -0.65
     Ivy
    -0.63
    POSITIVE LOGITS
    belt
    1.20
    holders
    1.08
     Seat
    1.02
    holder
    1.02
    mates
    1.00
    washer
    1.00
    seat
    0.98
    bars
    0.95
     cushion
    0.92
     cush
    0.91
    Act Density 0.023%

    No Known Activations