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

    Neuronpedia

    INDEX
    Explanations

    references to rationality and logical reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     International
    -0.46
     sed
    -0.46
     World
    -0.46
     Un
    -0.45
     Mac
    -0.43
     leg
    -0.43
     Cor
    -0.42
     Stra
    -0.42
     Kar
    -0.42
     Val
    -0.42
    POSITIVE LOGITS
     Италијани
    0.73
    сылкі
    0.72
    Rational
    0.68
     desmotivaciones
    0.68
    IntoConstraints
    0.67
    rational
    0.65
     logically
    0.65
    tagHelperRunner
    0.64
    expandindo
    0.62
     vectorielle
    0.60
    Act Density 0.601%

    No Known Activations