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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical actions like rolling up sleeves or rolling back regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the actions of rolling up or rolling back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auna
    -0.84
    nih
    -0.75
    edi
    -0.68
    blance
    -0.68
     Awakens
    -0.66
    oka
    -0.66
    uo
    -0.65
    orea
    -0.65
    hai
    -0.64
    xual
    -0.63
    POSITIVE LOGITS
     sleeves
    0.79
     shotgun
    0.75
     shoulders
    0.75
     stool
    0.69
     wire
    0.69
     canopy
    0.69
     suitcase
    0.68
     curtains
    0.68
     gates
    0.68
     hips
    0.68
    Act Density 0.090%

    No Known Activations