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

    Neuronpedia

    INDEX
    Explanations

    phrases related to skepticism and interpretation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skepticism and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    breaks
    -0.69
     succession
    -0.66
    redits
    -0.64
     haste
    -0.63
    ISO
    -0.62
     NCT
    -0.62
    keepers
    -0.61
     Bravo
    -0.60
     offic
    -0.60
     merging
    -0.59
    POSITIVE LOGITS
    icism
    1.34
    ively
    1.15
    ible
    1.13
    ical
    1.11
    acles
    1.10
    ibles
    1.10
    ics
    1.08
    acular
    1.08
    ibility
    1.03
    icons
    1.01
    Act Density 0.063%

    No Known Activations