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

    Neuronpedia

    INDEX
    Explanations

    words related to separation and distinctiveness

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     wonders
    -0.68
    enegger
    -0.68
    ãĥ¥
    -0.64
    herty
    -0.61
    nz
    -0.61
    mA
    -0.59
    bye
    -0.58
    rouse
    -0.57
    notation
    -0.57
    etics
    -0.56
    POSITIVE LOGITS
     separating
    0.80
     sexes
    0.77
     between
    0.77
     hairs
    0.76
     apart
    0.75
    owship
    0.74
     Between
    0.73
     from
    0.72
    aration
    0.72
    icular
    0.71
    Act Density 0.045%

    No Known Activations