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

    Neuronpedia

    INDEX
    Explanations

    references to different classes or types within a structured system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     withal
    -0.87
     poffible
    -0.85
    )++;
    -0.84
    devším
    -0.83
    eryllium
    -0.82
     neceffary
    -0.82
    }),
    -0.82
    ₁)
    -0.81
    })));
    -0.81
     Wanderers
    -0.80
    POSITIVE LOGITS
     Class
    1.88
     class
    1.81
     CLASS
    1.74
     classes
    1.74
    Class
    1.68
    class
    1.62
    CLASS
    1.54
     Classes
    1.52
    classes
    1.49
     classe
    1.33
    Act Density 0.107%

    No Known Activations