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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to oneself or others

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity and relationships with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odge
    -0.67
    ories
    -0.66
    rough
    -0.62
    iencies
    -0.62
     Safari
    -0.61
    FIG
    -0.61
    itialized
    -0.60
     Towns
    -0.58
    inctions
    -0.58
    1080
    -0.58
    POSITIVE LOGITS
     personally
    0.92
     selves
    0.83
    atics
    0.81
    atic
    0.81
     dearly
    0.78
    self
    0.78
    imei
    0.75
     verbally
    0.72
    andering
    0.70
    atis
    0.69
    Act Density 0.138%

    No Known Activations