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

    Neuronpedia

    INDEX
    Explanations

    references to entities or subjects within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ιβ
    -0.17
    dge
    -0.15
    426
    -0.15
     Chun
    -0.15
    733
    -0.15
    ümÃ¼ÅŁ
    -0.14
    ebra
    -0.14
    354
    -0.14
     Tie
    -0.14
     disp
    -0.14
    POSITIVE LOGITS
     schedule
    0.31
     lineup
    0.29
    agenda
    0.29
     spectrum
    0.27
    schedule
    0.26
     portfolio
    0.26
     roster
    0.26
     curriculum
    0.25
     menu
    0.25
     slate
    0.24
    Act Density 0.256%

    No Known Activations