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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing shared knowledge or experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "we all."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.71
    luster
    -0.65
     CLR
    -0.61
    IDS
    -0.60
    ichen
    -0.60
    clusive
    -0.57
     Lauder
    -0.57
     strang
    -0.57
     rarity
    -0.57
     Eag
    -0.56
    POSITIVE LOGITS
    ocating
    1.18
    ocated
    0.93
     kinds
    0.83
    together
    0.81
     smiles
    0.81
    edged
    0.79
    iances
    0.79
    usions
    0.78
     depended
    0.78
    owed
    0.76
    Act Density 0.044%

    No Known Activations