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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "unlimited"

    oai_token-act-pair · gpt-3.5-turbo

    references to unlimited resources or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -1.04
    acus
    -0.97
    pillar
    -0.83
    bourg
    -0.82
    Reviewed
    -0.80
    ector
    -0.78
    ect
    -0.75
    ective
    -0.75
    iffs
    -0.74
    nery
    -0.74
    POSITIVE LOGITS
     amounts
    1.10
     amount
    1.02
     quantities
    0.95
     access
    0.87
     regress
    0.87
     supply
    0.85
     Tsukuyomi
    0.84
     gratification
    0.82
     possibilities
    0.78
    urious
    0.76
    Act Density 0.046%

    No Known Activations