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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movement, such as sliding, pulling, pressing, pushing, and screwing

    oai_token-act-pair · gpt-3.5-turbo

    actions related to handling, moving, or manipulating objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    journal
    -0.68
    âĹ¼
    -0.67
    Campaign
    -0.63
    Reporting
    -0.61
     Invasion
    -0.59
     Pension
    -0.57
    reporting
    -0.57
     nationwide
    -0.57
    league
    -0.57
    Politics
    -0.57
    POSITIVE LOGITS
     downwards
    1.06
     levers
    1.01
     downward
    0.94
     them
    0.93
     onto
    0.92
     it
    0.91
     oneself
    0.87
    urized
    0.87
     gently
    0.87
     fingers
    0.86
    Act Density 0.220%

    No Known Activations