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

    Neuronpedia

    INDEX
    Explanations

    phrases related to internet links or references

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nuts
    -0.79
    eur
    -0.75
    eper
    -0.74
     foc
    -0.73
    ba
    -0.70
    obbies
    -0.69
     insult
    -0.68
    blers
    -0.67
     sill
    -0.67
     vanity
    -0.67
    POSITIVE LOGITS
    ————
    1.14
    ————————————————
    0.99
    ————————
    0.98
     Announce
    0.89
     Advertisement
    0.85
     Reporter
    0.84
     Posted
    0.83
     Featuring
    0.82
    Posted
    0.82
     Allows
    0.81
    Act Density 0.031%

    No Known Activations