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

    Neuronpedia

    INDEX
    Explanations

    references to stars and star-related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Obrador
    -0.84
     Cuenca
    -0.81
    adaptiveStyles
    -0.81
     Bourgoin
    -0.81
    expandindo
    -0.80
     Réponses
    -0.79
     ivelany
    -0.78
     ALC
    -0.76
    addGap
    -0.76
    iastes
    -0.75
    POSITIVE LOGITS
     Star
    2.35
     star
    2.29
     STAR
    2.27
     stars
    2.22
    Star
    2.15
    star
    2.11
     Stars
    2.11
    STAR
    2.07
    stars
    2.01
    Stars
    1.95
    Act Density 0.092%

    No Known Activations