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

    Neuronpedia

    INDEX
    Explanations

    terms related to well-establishment or confirmation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "established."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pe
    -0.71
    mith
    -0.71
    har
    -0.70
    CPU
    -0.70
    sol
    -0.70
    hop
    -0.69
    phe
    -0.69
    ertodd
    -0.68
    ÃŃa
    -0.68
    son
    -0.67
    POSITIVE LOGITS
    lishes
    1.04
    ablished
    0.95
    ablish
    0.90
     established
    0.90
    established
    0.90
     establishes
    0.89
     estab
    0.77
    iates
    0.75
     establish
    0.74
    ynski
    0.74
    Act Density 0.011%

    No Known Activations