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

    Neuronpedia

    INDEX
    Explanations

    verbs related to implementing or introducing a change or action

    oai_token-act-pair · gpt-3.5-turbo

    actions related to implementing changes or introducing new elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pring
    -0.77
    eem
    -0.75
    ems
    -0.75
    ogi
    -0.72
    esome
    -0.72
    Present
    -0.72
    present
    -0.72
    edly
    -0.71
    fortune
    -0.70
    ulet
    -0.70
    POSITIVE LOGITS
     stricter
    0.95
     fewer
    0.89
     rid
    0.89
     additional
    0.87
     tighter
    0.86
     existing
    0.83
     tougher
    0.83
     moratorium
    0.83
     foreigners
    0.79
     restrictions
    0.78
    Act Density 0.299%

    No Known Activations