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

    Neuronpedia

    INDEX
    Explanations

    references to authorities and official entities

    oai_token-act-pair · gpt-3.5-turbo

    references to authority figures or institutions, particularly those involved in law enforcement and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.74
    tery
    -0.67
    atre
    -0.65
     lives
    -0.61
     brisk
    -0.60
     Chau
    -0.59
    standing
    -0.57
     vanished
    -0.57
     wont
    -0.57
    achi
    -0.57
    POSITIVE LOGITS
     interviewer
    0.86
    ij士
    0.83
     inquire
    0.82
    DERR
    0.81
    è¦ļéĨĴ
    0.80
    mbuds
    0.79
     creditors
    0.73
    omever
    0.72
     detriment
    0.70
    strate
    0.70
    Act Density 0.708%

    No Known Activations