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

    Neuronpedia

    INDEX
    Explanations

    words related to wheels or wheel-related activities

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to wheels and related terms indicating mechanical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uates
    -0.79
    uated
    -0.77
     ABE
    -0.76
    ropolitan
    -0.75
    orescent
    -0.70
    raviolet
    -0.70
     Grounds
    -0.67
    ocado
    -0.67
     Suc
    -0.67
     Sunshine
    -0.67
    POSITIVE LOGITS
    chairs
    1.34
    chair
    1.25
    wright
    1.18
    wheel
    1.11
    base
    0.96
    wash
    0.92
    house
    0.89
    bar
    0.86
    horn
    0.85
    Wheel
    0.84
    Act Density 0.025%

    No Known Activations