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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions, especially focusing on the impact on others

    oai_token-act-pair · gpt-3.5-turbo

    phrases concerning personal or collective actions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bid
    -0.76
    mbuds
    -0.66
    inately
    -0.66
     AES
    -0.65
    anus
    -0.63
    ixed
    -0.61
    skinned
    -0.61
    owship
    -0.61
     Dise
    -0.61
    BLE
    -0.60
    POSITIVE LOGITS
     ACTIONS
    1.02
    uations
    1.00
     actions
    0.98
    uate
    0.92
    hops
    0.91
    uation
    0.89
    uated
    0.87
    ives
    0.85
    uits
    0.83
    ivism
    0.82
    Act Density 0.040%

    No Known Activations