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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the inability to do something

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of inability or reluctance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.67
     sidx
    -0.66
    imity
    -0.63
    assault
    -0.63
     espionage
    -0.61
     Hunters
    -0.61
     Invasion
    -0.59
    ranged
    -0.58
     ancestor
    -0.58
    pires
    -0.58
    POSITIVE LOGITS
     imagine
    1.18
    athom
    1.12
     afford
    1.08
     remember
    0.96
     believe
    0.94
     conceive
    0.94
     quantify
    0.91
     say
    0.88
     emphasize
    0.87
     compare
    0.86
    Act Density 0.103%

    No Known Activations