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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical description and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its context within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     based
    -0.76
    thood
    -0.76
    omics
    -0.70
    America
    -0.68
    Policy
    -0.68
     versus
    -0.67
     argues
    -0.65
    bourg
    -0.65
    cially
    -0.65
     distinguishes
    -0.65
    POSITIVE LOGITS
     latter
    1.20
     remainder
    1.14
     slightest
    1.11
     entire
    1.04
     nearest
    1.02
     same
    1.02
     smallest
    1.02
    ses
    1.01
     aforementioned
    0.97
     ensuing
    0.97
    Act Density 0.925%

    No Known Activations