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

    Neuronpedia

    INDEX
    Explanations

    commands related to deleting and removing items or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.92
    ConstraintMaker
    -0.74
    Personensuche
    -0.64
     autorytatywna
    -0.62
     LoggerFactory
    -0.61
    textTheme
    -0.60
     مشين
    -0.59
    CAPTION
    -0.59
    сылкі
    -0.57
    bewerken
    -0.56
    POSITIVE LOGITS
     unnecessary
    0.99
     superfluous
    0.90
     khỏi
    0.89
     unwanted
    0.83
     excess
    0.81
     offending
    0.80
     redundant
    0.78
     inneces
    0.76
     excesso
    0.74
     unprofitable
    0.72
    Act Density 0.466%

    No Known Activations