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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpersonal relationships and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enders
    -0.14
    oust
    -0.13
    enc
    -0.13
    лÑıÑħ
    -0.13
    licative
    -0.12
    ongan
    -0.12
    ennon
    -0.12
    ottes
    -0.12
    unik
    -0.12
    dent
    -0.12
    POSITIVE LOGITS
     multiple
    1.06
    multiple
    0.92
     Multiple
    0.90
    Multiple
    0.85
    _multiple
    0.73
    å¤ļ
    0.70
    ultiple
    0.69
     several
    0.59
     å¤ļ
    0.57
     ìŬ룬
    0.55
    Act Density 0.632%

    No Known Activations