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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical restraint or positioning of objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "sit" and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idge
    -0.72
    phies
    -0.71
    killer
    -0.70
    agic
    -0.69
    iles
    -0.68
    phy
    -0.67
    aceutical
    -0.67
    meta
    -0.65
    age
    -0.65
    isks
    -0.63
    POSITIVE LOGITS
    utenant
    0.88
    ratulations
    0.72
     Forces
    0.65
     nomine
    0.65
     against
    0.65
    square
    0.64
    wic
    0.62
     commanders
    0.62
    arity
    0.61
    raged
    0.61
    Act Density 0.057%

    No Known Activations