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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the state or attribute of being

    oai_token-act-pair · gpt-3.5-turbo

    frequent uses of the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Highlights
    -0.71
     reacts
    -0.67
    ibilities
    -0.67
    ities
    -0.66
     Inventory
    -0.65
    ukong
    -0.64
    ITIES
    -0.63
    Comments
    -0.63
    regate
    -0.63
     Join
    -0.62
    POSITIVE LOGITS
     technically
    1.02
    nt
    0.98
     unlikely
    0.93
     relatively
    0.93
     observational
    0.88
     harmless
    0.87
     purely
    0.86
     subjective
    0.86
     sensitive
    0.85
     intrinsically
    0.84
    Act Density 0.431%

    No Known Activations