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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing desire or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Extras
    -0.17
    oud
    -0.15
    912
    -0.14
    gles
    -0.14
    nga
    -0.14
    ady
    -0.14
    کت
    -0.14
    rapper
    -0.14
    sein
    -0.13
    adu
    -0.13
    POSITIVE LOGITS
    igr
    0.18
     permission
    0.15
    ardon
    0.15
     assistance
    0.15
     бÑĥдÑĮ
    0.14
    gnore
    0.14
    alta
    0.14
    æ²¢
    0.14
    quam
    0.14
    ffective
    0.14
    Act Density 0.027%

    No Known Activations