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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     veía
    -0.50
     appris
    -0.43
     étrangères
    -0.42
    orte
    -0.41
    licitations
    -0.40
    tică
    -0.40
     Hygiene
    -0.40
    ジュアル
    -0.40
    endtime
    -0.40
     informed
    -0.39
    POSITIVE LOGITS
     myſelf
    0.72
    complexContent
    0.71
     Monfieur
    0.69
     Efq
    0.67
    Portail
    0.67
    Portale
    0.66
     uſe
    0.65
     Perſ
    0.64
    kuuta
    0.63
     Reſ
    0.63
    Act Density 0.002%

    No Known Activations