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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Those"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "Those."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILY
    -0.80
    kamp
    -0.79
    efully
    -0.77
    osate
    -0.77
    PLA
    -0.77
    HY
    -0.75
    abis
    -0.75
    ob
    -0.74
    enegger
    -0.74
    ¨
    -0.69
    POSITIVE LOGITS
     pesky
    1.07
     wishing
    1.00
     who
    0.94
     kinds
    0.93
     sentiments
    0.86
     wanting
    0.84
     statements
    0.84
     thoughts
    0.83
     feelings
    0.82
     distinctions
    0.81
    Act Density 0.071%

    No Known Activations