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

    Neuronpedia

    INDEX
    Explanations

    multi-word phrases related to people and their characteristics or actions, particularly those relating to medical conditions or social situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "people" along with related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quantity
    -0.70
     successor
    -0.58
    INAL
    -0.55
     Collider
    -0.55
    UCT
    -0.54
    ãĥ´ãĤ¡
    -0.54
    soDeliveryDate
    -0.54
     predecessor
    -0.54
    ãĥ¼ãĥĨ
    -0.53
    éĹ
    -0.53
    POSITIVE LOGITS
     themselves
    0.74
    vae
    0.64
     whom
    0.63
     congreg
    0.61
    pees
    0.61
    who
    0.59
    conserv
    0.58
     alike
    0.57
     theirs
    0.57
    doms
    0.56
    Act Density 2.494%

    No Known Activations