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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and political contexts

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     followed
    -0.69
     Takes
    -0.61
    .–
    -0.61
    /-
    -0.60
     sprang
    -0.59
     strives
    -0.59
     according
    -0.59
     compared
    -0.59
    rand
    -0.58
    packages
    -0.58
    POSITIVE LOGITS
     extent
    1.28
     fullest
    1.22
     detriment
    1.10
     same
    1.05
     forefront
    0.97
     lowest
    0.96
     highest
    0.96
     depths
    0.95
     utmost
    0.95
     nearest
    0.94
    Act Density 0.254%

    No Known Activations