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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making and uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whether"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Catalog
    -1.02
    UX
    -0.80
    oven
    -0.76
    sung
    -0.72
    lator
    -0.72
    oxide
    -0.70
    ãĤ¨ãĥ«
    -0.70
    apt
    -0.69
    Eye
    -0.68
    icker
    -0.67
    POSITIVE LOGITS
    soever
    0.90
     they
    0.77
     there
    0.70
    fy
    0.68
     servic
    0.66
    terday
    0.65
     judges
    0.64
     he
    0.64
     respondents
    0.63
     we
    0.63
    Act Density 0.034%

    No Known Activations