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

    Neuronpedia

    INDEX
    Explanations

    references to support and encourage others, often in a context of social or community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AxisAlignment
    -0.70
    に対し
    -0.67
     såsom
    -0.64
     genomen
    -0.61
     tevens
    -0.60
     lediglich
    -0.59
     gesteld
    -0.57
    となっている
    -0.56
     endast
    -0.56
     regarding
    -0.54
    POSITIVE LOGITS
     stuff
    0.89
    GEBURTSDATUM
    0.89
     ugly
    0.81
     scared
    0.74
    تقاوى
    0.74
     scary
    0.71
     darn
    0.70
     dirty
    0.70
     Мексичка
    0.70
    IntoConstraints
    0.70
    Act Density 0.862%

    No Known Activations