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

    Neuronpedia

    INDEX
    Explanations

    superlatives describing size or importance

    oai_token-act-pair · gpt-3.5-turbo

    the term "biggest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ences
    -0.76
    heid
    -0.75
    jad
    -0.72
    isson
    -0.72
    icing
    -0.70
    schild
    -0.70
    ency
    -0.69
    manship
    -0.68
    perty
    -0.68
    anism
    -0.68
    POSITIVE LOGITS
    gest
    1.03
     culprit
    0.89
     bang
    0.88
     offender
    0.84
     obstacle
    0.82
     chunk
    0.81
     proponent
    0.77
     payoff
    0.77
     loser
    0.76
     hurdle
    0.75
    Act Density 0.018%

    No Known Activations