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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conflicts or disagreements between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of contention or disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uum
    -0.97
    hesis
    -0.73
    illary
    -0.73
    OH
    -0.71
    ï¸
    -0.69
    osphere
    -0.67
    KE
    -0.67
    osis
    -0.67
    uity
    -0.65
    uary
    -0.63
    POSITIVE LOGITS
    tones
    1.12
    haul
    0.92
    hang
    0.92
    loading
    0.92
    lord
    0.87
    reaching
    0.87
    priced
    0.84
    comes
    0.84
    capacity
    0.80
    drive
    0.80
    Act Density 0.057%

    No Known Activations