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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legal classifications of offenses and regulatory standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardin
    -0.15
    idar
    -0.14
    aggio
    -0.14
    zion
    -0.14
    лÑĥг
    -0.13
    arden
    -0.13
    κολ
    -0.13
    hcp
    -0.13
    .scalablytyped
    -0.13
    γα
    -0.13
    POSITIVE LOGITS
     falls
    0.63
     fall
    0.62
     falling
    0.54
     FALL
    0.53
    fall
    0.53
     Fall
    0.52
    falls
    0.51
    Fall
    0.49
     qualify
    0.47
     fallen
    0.46
    Act Density 0.405%

    No Known Activations