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

    Neuronpedia

    INDEX
    Explanations

    personal development and self-improvement-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of self or personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.71
    apo
    -0.69
    origin
    -0.67
    meat
    -0.67
    emis
    -0.65
    olid
    -0.64
     [+
    -0.63
     Rail
    -0.62
    economic
    -0.62
     Mub
    -0.62
    POSITIVE LOGITS
    selves
    0.98
    tub
    0.92
     yourself
    0.80
     mate
    0.77
     guys
    0.74
    ocard
    0.73
     selves
    0.73
     yourselves
    0.71
    RS
    0.70
    ãģ§
    0.66
    Act Density 0.017%

    No Known Activations