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

    Neuronpedia

    INDEX
    Explanations

    specific instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to recommendations and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imposed
    -0.84
    alos
    -0.80
    enos
    -0.79
    gemony
    -0.71
    ternity
    -0.70
    xual
    -0.69
    forth
    -0.69
    utra
    -0.69
    ochond
    -0.67
    abiding
    -0.67
    POSITIVE LOGITS
     Accessories
    1.05
     Items
    1.03
     Mods
    0.86
     Products
    0.86
     extras
    0.83
     accessories
    0.83
     Features
    0.81
     accessory
    0.79
     items
    0.78
     Extras
    0.76
    Act Density 0.091%

    No Known Activations