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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.15
     supposed
    -0.15
    yon
    -0.14
    /process
    -0.14
    uba
    -0.14
     alleged
    -0.14
     purported
    -0.14
    -resource
    -0.13
    appen
    -0.13
    rex
    -0.13
    POSITIVE LOGITS
     they
    0.18
    rames
    0.16
    asd
    0.15
     Preis
    0.14
    bb
    0.14
     dort
    0.14
    usi
    0.14
    ãĥ³ãĥĩãĤ£
    0.13
     there
    0.13
    0.13
    Act Density 0.014%

    No Known Activations