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

    Neuronpedia

    INDEX
    Explanations

    terms related to significant or notable events or developments

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to significant agreements, models, or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -1.08
    brids
    -0.90
    ources
    -0.86
    ourning
    -0.84
    anders
    -0.82
    aves
    -0.81
    iths
    -0.80
    Ģ
    -0.80
    rosso
    -0.80
    arus
    -0.79
    POSITIVE LOGITS
     moment
    0.83
     tactic
    0.83
     attraction
    0.82
     achievement
    0.81
     item
    0.78
     of
    0.77
     employer
    0.77
     project
    0.76
     idea
    0.75
     ingredient
    0.75
    Act Density 0.338%

    No Known Activations