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

    Neuronpedia

    INDEX
    Explanations

    phrases related to impactful consequences or effects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of impact or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /?
    -0.63
    anka
    -0.61
    uld
    -0.60
    erg
    -0.59
     drawback
    -0.57
    ikk
    -0.55
     Introduced
    -0.55
     Volunte
    -0.54
     Funds
    -0.53
     Problems
    -0.53
    POSITIVE LOGITS
     virtually
    1.21
     precisely
    1.08
     scarcely
    1.06
     EVERY
    1.04
     vastly
    1.03
     infinitely
    1.02
     everything
    1.02
     everywhere
    1.02
     literally
    1.01
     practically
    1.01
    Act Density 0.801%

    No Known Activations