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

    Neuronpedia

    INDEX
    Explanations

    concepts related to division or distinction between different entities or categories

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herty
    -0.72
    roll
    -0.65
    etics
    -0.64
     wonders
    -0.63
    enegger
    -0.63
    rouse
    -0.62
    OD
    -0.62
    odder
    -0.62
    fly
    -0.62
    å¸
    -0.62
    POSITIVE LOGITS
     separating
    0.92
     between
    0.91
     hairs
    0.82
     separ
    0.81
    aration
    0.80
     sexes
    0.80
    separ
    0.80
     Between
    0.79
    owship
    0.77
     separates
    0.75
    Act Density 0.037%

    No Known Activations