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

    Neuronpedia

    INDEX
    Explanations

    superlatives indicating the highest level or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that highlight extreme or superlative characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghai
    -0.89
    abus
    -0.82
    skirts
    -0.76
    uador
    -0.75
    amsung
    -0.69
    arth
    -0.69
    ocene
    -0.68
    arthy
    -0.64
    ichen
    -0.64
    orks
    -0.63
    POSITIVE LOGITS
     adversary
    1.00
     rivals
    0.98
     ally
    0.97
     asset
    0.97
     foray
    0.95
     rival
    0.94
     competitor
    0.92
     sibling
    0.91
     adversaries
    0.90
     selves
    0.90
    Act Density 0.156%

    No Known Activations