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

    Neuronpedia

    INDEX
    Explanations

    references to memory addresses or address indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )();
    -0.57
     gap
    -0.57
    ('');
    -0.56
    ...]
    -0.56
    ='')
    -0.56
     ());
    -0.55
    …)
    -0.54
     fal
    -0.54
    '))
    -0.54
    '])
    -0.54
    POSITIVE LOGITS
    enumi
    1.03
     &___
    0.98
     feroit
    0.96
    (&
    0.94
    InjectAttribute
    0.92
     étoient
    0.91
     avoient
    0.91
    ValueStyle
    0.88
     auroit
    0.85
     trouvera
    0.85
    Act Density 0.058%

    No Known Activations