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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belonging or being part of a group or community

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize belonging or being part of a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     assumes
    -0.66
     ceilings
    -0.65
    ptive
    -0.65
     incurred
    -0.63
     withd
    -0.62
     directs
    -0.61
     spouses
    -0.60
    culosis
    -0.60
    iasis
    -0.59
    ants
    -0.58
    POSITIVE LOGITS
    ¬¼
    0.72
     the
    0.70
     Team
    0.70
    İĭ
    0.68
    Team
    0.68
    axy
    0.67
    ģĸ
    0.67
     something
    0.66
     Kinnikuman
    0.65
    circle
    0.64
    Act Density 0.101%

    No Known Activations