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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to ordering or requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĥн
    -0.19
    för
    -0.16
    ulously
    -0.15
    kö
    -0.15
    aille
    -0.15
    INDER
    -0.14
    /her
    -0.14
    plied
    -0.14
    inerary
    -0.14
    кÑĥÑĢ
    -0.14
    POSITIVE LOGITS
    liness
    0.21
    edList
    0.20
    iginal
    0.17
    heim
    0.17
    iffin
    0.16
    .scalablytyped
    0.16
    ments
    0.16
    wide
    0.15
    IENTATION
    0.15
    ourke
    0.15
    Act Density 0.052%

    No Known Activations