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

    Neuronpedia

    INDEX
    Explanations

    statements of assertion or claim

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to asserting opinions or rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vation
    -0.72
    osponsors
    -0.64
    bered
    -0.63
     Bake
    -0.63
    otide
    -0.63
     Exper
    -0.62
     Shotgun
    -0.62
    behind
    -0.61
     Seat
    -0.61
     Redemption
    -0.59
    POSITIVE LOGITS
     assert
    1.34
    assert
    1.22
    ieth
    1.08
    iveness
    1.08
    ively
    1.01
    ignty
    0.95
     asserts
    0.94
     asserting
    0.91
    weak
    0.88
    ilian
    0.85
    Act Density 0.006%

    No Known Activations