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

    Neuronpedia

    INDEX
    Explanations

    instances of comparative language and references to groups or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¯
    -0.17
     Robbins
    -0.16
    inus
    -0.15
    ooks
    -0.15
    edii
    -0.15
    assi
    -0.14
    asil
    -0.14
     Jennings
    -0.14
    ective
    -0.14
    вали
    -0.13
    POSITIVE LOGITS
     respectively
    0.32
     respective
    0.22
     ÑģооÑĤвеÑĤ
    0.19
     PI
    0.17
    GI
    0.15
    ihan
    0.15
    isted
    0.15
    otos
    0.15
    emet
    0.15
    eling
    0.14
    Act Density 0.061%

    No Known Activations