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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the creation or construction of objects or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to structures or systems related to identity and their interaction within established frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.76
     Barron
    -0.70
    ellen
    -0.69
    ntil
    -0.65
    jri
    -0.63
    imon
    -0.63
    pedia
    -0.63
    ventus
    -0.62
     âĨij
    -0.62
    Õ
    -0.62
    POSITIVE LOGITS
     eman
    0.74
     caus
    0.74
     chosen
    0.72
     intended
    0.71
     respective
    0.71
     desired
    0.70
     perce
    0.68
     wearer
    0.68
     transmissions
    0.67
     propag
    0.67
    Act Density 0.716%

    No Known Activations