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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to natural characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts and phrases related to the idea of being natural or instinctual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eworks
    -0.72
    raph
    -0.70
    arij
    -0.67
    andals
    -0.66
    burgh
    -0.64
    packages
    -0.64
     Millennium
    -0.63
    mm
    -0.63
    ificantly
    -0.63
    mmm
    -0.63
    POSITIVE LOGITS
     occurring
    1.09
     progression
    0.99
     instinct
    0.98
    istic
    0.97
     consequence
    0.96
     grav
    0.89
    occ
    0.85
     inclination
    0.84
     occurrence
    0.80
     tendency
    0.79
    Act Density 0.060%

    No Known Activations