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

    Neuronpedia

    INDEX
    Explanations

    references to work and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.72
    HtmlAttribute
    -0.72
    Datuak
    -0.67
    NoSuchAlgorithm
    -0.59
     Sache
    -0.57
     numberWith
    -0.57
     Lindberg
    -0.57
    Tup
    -0.57
    Pautan
    -0.56
     BrowserModule
    -0.55
    POSITIVE LOGITS
     ethic
    0.80
    horse
    0.77
     done
    0.76
    aday
    0.69
    horses
    0.67
    spaces
    0.67
    done
    0.64
    site
    0.64
    forces
    0.62
    manship
    0.62
    Act Density 0.118%

    No Known Activations