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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies or public affairs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDF
    -0.68
     Awakens
    -0.67
    orb
    -0.66
     Oo
    -0.64
    craft
    -0.63
    blogspot
    -0.63
    pdf
    -0.62
    jen
    -0.61
    olla
    -0.61
    orns
    -0.60
    POSITIVE LOGITS
    idth
    0.69
    blance
    0.64
     Chamberlain
    0.60
    EMBER
    0.60
    é¾įå¥ij士
    0.59
    vernment
    0.58
    ignty
    0.57
     sheer
    0.56
    Magikarp
    0.56
    ULE
    0.56
    Act Density 0.538%

    No Known Activations