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

    Neuronpedia

    INDEX
    Explanations

    terms related to breaking or disruption

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal concepts and violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arthy
    -0.65
     attendant
    -0.63
    eton
    -0.63
     moderators
    -0.62
    soDeliveryDate
    -0.60
     proceeds
    -0.58
     vetoed
    -0.57
    tarians
    -0.57
     sparing
    -0.56
    ppe
    -0.56
    POSITIVE LOGITS
     membranes
    0.78
     membrane
    0.75
    Wan
    0.71
     cycle
    0.67
    sheets
    0.66
     polymer
    0.66
    Sax
    0.66
    hibited
    0.65
    mol
    0.64
    into
    0.63
    Act Density 0.129%

    No Known Activations