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

    Neuronpedia

    INDEX
    Explanations

    strong action verbs and nouns related to legal or official procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.75
     srf
    -0.71
    iolet
    -0.60
    osponsors
    -0.58
     corners
    -0.57
     appet
    -0.56
    Weather
    -0.56
     pree
    -0.55
    ãĤ«
    -0.54
    adow
    -0.54
    POSITIVE LOGITS
     anew
    0.97
    liest
    0.79
    enium
    0.78
     anonymously
    0.77
     WITHOUT
    0.76
     myself
    0.76
    washer
    0.76
     willingly
    0.74
    iest
    0.73
     beforehand
    0.73
    Act Density 0.374%

    No Known Activations