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

    Neuronpedia

    INDEX
    Explanations

    examples and instances related to explanations or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }],
    -0.85
    ...");
    -0.79
    frastructure
    -0.75
     configureStore
    -0.74
    ulongan
    -0.74
     Monfieur
    -0.72
     whoſe
    -0.72
     themſelves
    -0.71
    UAGE
    -0.70
     bershka
    -0.69
    POSITIVE LOGITS
     example
    1.59
    example
    1.34
     Example
    1.28
    Example
    1.27
     ejemplo
    1.27
     exemple
    1.22
     Beispiel
    1.22
     esempio
    1.21
     exemplo
    1.21
    EXAMPLE
    1.20
    Act Density 0.278%

    No Known Activations