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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that praise or approve of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or commendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occupied
    -0.83
    bourne
    -0.75
    flow
    -0.72
    ther
    -0.72
    pos
    -0.71
     residue
    -0.71
    infect
    -0.69
    quickShipAvailable
    -0.69
    bad
    -0.68
    omore
    -0.68
    POSITIVE LOGITS
     applauded
    1.21
     praised
    1.00
     applaud
    0.99
     lauded
    0.95
     praise
    0.88
     commend
    0.87
     praising
    0.87
     praises
    0.86
     congratulated
    0.85
     virtues
    0.81
    Act Density 0.024%

    No Known Activations