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

    Neuronpedia

    INDEX
    Explanations

    references to specific sources or citations within a text

    oai_token-act-pair · gpt-3.5-turbo

    citations or references to sources and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apon
    -0.80
    soever
    -0.74
    ieu
    -0.66
    Sphere
    -0.61
    pires
    -0.60
    UME
    -0.59
    Enter
    -0.59
     Females
    -0.58
     Veg
    -0.57
    Fuck
    -0.57
    POSITIVE LOGITS
     precedent
    0.89
     preced
    0.89
     similarities
    0.85
     playbook
    0.85
     Cosponsors
    0.84
     sources
    0.80
     anecdotal
    0.78
     example
    0.77
     inaccur
    0.77
     firsthand
    0.75
    Act Density 0.430%

    No Known Activations