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

    Neuronpedia

    INDEX
    Explanations

    actions or tasks being performed

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performing actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.91
    izons
    -0.81
    encers
    -0.70
     publishers
    -0.66
     horizon
    -0.66
     porous
    -0.66
    assadors
    -0.64
     manufacturers
    -0.63
    urers
    -0.62
     dealers
    -0.62
    POSITIVE LOGITS
     tasks
    1.24
     rituals
    1.09
     duties
    1.08
     maneuvers
    1.05
     manoeuv
    1.04
     ritual
    1.03
     chores
    1.03
     feats
    1.00
     stunts
    1.00
     rites
    1.00
    Act Density 0.376%

    No Known Activations