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

    Neuronpedia

    INDEX
    Explanations

    superlatives or things with a historical or significant importance

    oai_token-act-pair · gpt-3.5-turbo

    superlative descriptors related to age, size, and uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asions
    -0.89
    votes
    -0.86
    bags
    -0.78
    iencies
    -0.77
    rants
    -0.75
    eds
    -0.74
    chers
    -0.74
    Keys
    -0.73
    runs
    -0.73
    Numbers
    -0.73
    POSITIVE LOGITS
     extant
    1.12
     standalone
    0.96
     surviving
    0.96
     installment
    0.92
     comprehensive
    0.91
     commercially
    0.88
     sanctioned
    0.87
     documented
    0.84
     foray
    0.84
     continuously
    0.83
    Act Density 0.180%

    No Known Activations