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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transportation vehicles or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to vehicles and objects involved in incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Helpful
    -0.84
     Flavoring
    -0.73
     "$:/
    -0.71
     Teams
    -0.70
    cffff
    -0.68
     Interest
    -0.68
    20439
    -0.67
     Spending
    -0.67
    emonic
    -0.67
    ync
    -0.66
    POSITIVE LOGITS
     belonged
    1.37
     disappeared
    1.09
     belongs
    1.04
     vanished
    1.01
     appeared
    1.01
     was
    0.99
     consisted
    0.98
     lasted
    0.97
     survived
    0.96
     exploded
    0.96
    Act Density 0.305%

    No Known Activations