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

    Neuronpedia

    INDEX
    Explanations

    statements indicating a timeless or never-ending duration

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate a lack of limitations or permanence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dll
    -0.61
    uka
    -0.60
     typ
    -0.58
     CTR
    -0.57
     Blossom
    -0.57
     Blitz
    -0.56
     Rider
    -0.56
    osi
    -0.56
    ilar
    -0.56
     clicked
    -0.54
    POSITIVE LOGITS
     indefinitely
    3.90
     indefinite
    1.85
     forever
    1.54
     arbitrarily
    1.40
     endlessly
    1.25
     infinitely
    1.23
     permanently
    1.16
     temporarily
    1.11
     unilaterally
    0.97
     exponentially
    0.95
    Act Density 0.012%

    No Known Activations