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

    Neuronpedia

    INDEX
    Explanations

    phrases related to risk, uncertainty, and regulatory disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     merit
    -0.49
     criss
    -0.48
     holy
    -0.48
    #+#
    -0.48
     domain
    -0.48
     middle
    -0.47
     square
    -0.47
     memoir
    -0.47
     chief
    -0.47
     footprint
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.66
     Anſ
    0.59
     prêtres
    0.57
    middels
    0.56
     ModelExpression
    0.54
     nødven
    0.53
     Reſ
    0.53
     mijne
    0.53
     ſtand
    0.52
     Perſ
    0.52
    Act Density 0.672%

    No Known Activations