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

    Neuronpedia

    INDEX
    Explanations

    references to authority or decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seems
    -0.64
     seems
    -0.63
     lijkt
    -0.62
     Surely
    -0.60
     creo
    -0.59
     claro
    -0.58
     confirms
    -0.58
     понять
    -0.57
     glaube
    -0.57
     confirm
    -0.56
    POSITIVE LOGITS
    IntoConstraints
    1.02
    ConstraintMaker
    1.01
     ویکی‌پدیای
    0.85
    ScopeManager
    0.84
    ."));
    0.80
     MainAxisSize
    0.79
     GenerationType
    0.77
     BorderRadius
    0.77
     Normdatei
    0.76
    makeConstraints
    0.76
    Act Density 0.400%

    No Known Activations