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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal preferences or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong personal identity and self-description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disappear
    -0.69
     vanish
    -0.66
     indefinitely
    -0.66
     scrimmage
    -0.66
     Regions
    -0.64
    VERTISEMENT
    -0.64
     advances
    -0.63
     allocations
    -0.62
    enges
    -0.62
    çķ
    -0.61
    POSITIVE LOGITS
     lucky
    0.93
     believer
    0.91
     myself
    0.91
     fortunate
    0.84
     proud
    0.80
    opic
    0.76
     skept
    0.73
     obsessed
    0.73
     skeptical
    0.72
    strong
    0.71
    Act Density 0.230%

    No Known Activations