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

    Neuronpedia

    INDEX
    Explanations

    phrases related to praising or commending

    oai_token-act-pair · gpt-3.5-turbo

    instances of praise and admiration directed towards individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nel
    -0.82
    itol
    -0.74
    matter
    -0.70
    tails
    -0.68
    iba
    -0.66
    alde
    -0.64
    netflix
    -0.64
    ombs
    -0.63
    claimer
    -0.60
     Hayward
    -0.60
    POSITIVE LOGITS
     accomplishments
    1.12
     accomplishment
    1.09
     virtues
    1.06
     bravery
    1.04
     achievements
    1.01
     courage
    0.96
     professionalism
    0.92
     heroism
    0.92
     achievement
    0.92
     successes
    0.90
    Act Density 0.229%

    No Known Activations