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

    Neuronpedia

    INDEX
    Explanations

    references to a specific entity or name, likely related to a scholarly or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poffe
    -1.10
     raiſ
    -1.03
     myſelf
    -1.02
     poffible
    -0.94
    ViewFeatures
    -0.92
     ſhe
    -0.91
     iſt
    -0.90
     juſt
    -0.89
     faſt
    -0.86
     becauſe
    -0.86
    POSITIVE LOGITS
    Sch
    3.13
     Sch
    3.10
     sch
    2.89
    sch
    2.69
     SCH
    2.38
    SCH
    2.23
    scho
    1.53
     Scho
    1.51
     Schl
    1.50
    ensch
    1.48
    Act Density 0.042%

    No Known Activations