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

    Neuronpedia

    INDEX
    Explanations

    incomplete words with a distinctive pattern

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.82
    tnc
    -0.75
    bled
    -0.72
    ade
    -0.70
    bed
    -0.69
    die
    -0.69
    SPONSORED
    -0.69
    rium
    -0.69
    INS
    -0.69
    ursed
    -0.68
    POSITIVE LOGITS
     acknowledging
    1.21
     researching
    1.07
     conced
    0.95
     browsing
    0.93
     discussing
    0.92
     admitting
    0.89
     maintaining
    0.86
     agreeing
    0.85
     dismissing
    0.85
     respecting
    0.85
    Act Density 0.058%

    No Known Activations