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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging or discouraging specific behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that encourage positive behaviors and attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.63
     Explosion
    -0.62
     Prescott
    -0.62
     Lines
    -0.61
     suffice
    -0.60
     reconstruction
    -0.60
     Topics
    -0.60
     Strait
    -0.59
     autopsy
    -0.59
     fray
    -0.59
    POSITIVE LOGITS
     able
    1.14
     thankful
    1.13
     aware
    1.09
     afraid
    1.02
     honest
    1.01
     grateful
    1.01
     careful
    1.01
    friends
    0.96
     ashamed
    0.96
     proud
    0.95
    Act Density 0.167%

    No Known Activations