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

    Neuronpedia

    INDEX
    Explanations

    words related to entertainment or media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bjerg
    -0.17
    zell
    -0.15
    pill
    -0.15
     λι
    -0.15
    nP
    -0.14
    Ùħ
    -0.14
     Wein
    -0.14
    È
    -0.14
    losures
    -0.14
    169
    -0.14
    POSITIVE LOGITS
    igon
    0.16
    atto
    0.15
     Covered
    0.15
    stin
    0.14
     material
    0.14
     ARP
    0.14
    UDA
    0.14
    icator
    0.14
     mass
    0.14
    strtolower
    0.14
    Act Density 0.000%

    No Known Activations