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

    Neuronpedia

    INDEX
    Explanations

    references to specific sources in a formal manner

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "according to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.83
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    ctor
    -0.67
    ograp
    -0.67
    ONSORED
    -0.65
    gage
    -0.64
    estern
    -0.64
    icably
    -0.63
    atically
    -0.63
    anooga
    -0.63
    POSITIVE LOGITS
     Reuters
    0.84
     sources
    0.73
     EW
    0.72
     DSM
    0.71
     Forbes
    0.70
     Kant
    0.70
     according
    0.69
     paraph
    0.68
     eyewitness
    0.68
     CNBC
    0.68
    Act Density 0.069%

    No Known Activations