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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases involving the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĭÑģ
    -0.16
    ovenant
    -0.15
    odium
    -0.15
    recision
    -0.15
    ÑĦÑĦ
    -0.15
    ceb
    -0.15
    çļ
    -0.14
     Oven
    -0.14
    urma
    -0.14
     Sap
    -0.14
    POSITIVE LOGITS
    ansen
    0.16
    /TT
    0.16
     Ple
    0.16
    ees
    0.14
    aging
    0.14
    ilon
    0.14
    Ł
    0.14
     reasons
    0.14
    illac
    0.14
     lunch
    0.13
    Act Density 0.109%

    No Known Activations