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

    Neuronpedia

    INDEX
    Explanations

    phrases related to objects or entities in a sentence that can be the focus of attention

    oai_token-act-pair · gpt-3.5-turbo

    references to objects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.79
    NPR
    -0.76
    ornia
    -0.75
    mph
    -0.72
    ricia
    -0.70
    egal
    -0.69
    lla
    -0.67
    heit
    -0.66
    corn
    -0.66
    ndra
    -0.65
    POSITIVE LOGITS
    imus
    0.99
    ivity
    0.98
    ively
    0.91
     objects
    0.86
    ishly
    0.85
    ives
    0.84
    objects
    0.83
    ification
    0.83
    ifications
    0.82
    ivist
    0.82
    Act Density 0.026%

    No Known Activations