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

    Neuronpedia

    INDEX
    Explanations

    sentences describing something subtle or minor

    oai_token-act-pair · gpt-3.5-turbo

    instances of mild or minor changes or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.82
    CDC
    -0.74
    tested
    -0.65
     Ready
    -0.64
     Chronic
    -0.64
    ceans
    -0.64
     convened
    -0.62
    answered
    -0.62
    halla
    -0.62
     Kardash
    -0.61
    POSITIVE LOGITS
     slight
    0.88
     exaggeration
    0.82
     modification
    0.79
     annoyance
    0.78
    nesses
    0.76
     resemblance
    0.76
     sway
    0.74
    rance
    0.73
     inclination
    0.73
    ihad
    0.73
    Act Density 0.009%

    No Known Activations