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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.04
     Jefus
    -0.92
     becauſe
    -0.89
     Chriftian
    -0.85
     Efq
    -0.81
     themſelves
    -0.80
     ſeveral
    -0.79
     fevere
    -0.78
     Diſ
    -0.78
     purpoſe
    -0.78
    POSITIVE LOGITS
     going
    1.02
     also
    0.99
     able
    0.98
     not
    0.95
     always
    0.94
     seen
    0.93
    RegistryLite
    0.93
     gonna
    0.87
     considered
    0.87
     just
    0.85
    Act Density 0.296%

    No Known Activations