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

    Neuronpedia

    INDEX
    Explanations

    lists or collections of items or information

    oai_token-act-pair · gpt-3.5-turbo

    lists or sequences of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roth
    -0.81
    transfer
    -0.74
    adr
    -0.73
    adra
    -0.72
    ulz
    -0.71
    icum
    -0.70
    uchi
    -0.70
    alysed
    -0.67
    orate
    -0.67
    cffffcc
    -0.67
    POSITIVE LOGITS
     Helpful
    0.90
     Tips
    0.87
     Reasons
    0.84
     Worst
    0.80
     tips
    0.80
     myths
    0.79
    ottest
    0.79
     Cele
    0.76
     Maxim
    0.76
     Foods
    0.73
    Act Density 0.277%

    No Known Activations