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

    Neuronpedia

    INDEX
    Explanations

    references to dogs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "og."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.77
     Michaels
    -0.71
    IDENT
    -0.70
    ensional
    -0.66
     Leilan
    -0.65
     apprehension
    -0.60
    staking
    -0.60
     calculus
    -0.59
    ¬¼
    -0.59
    wcs
    -0.58
    POSITIVE LOGITS
    gers
    1.20
    gy
    1.16
    roup
    1.14
    roups
    1.13
    raphic
    1.06
    ogo
    1.04
    ues
    1.02
    allery
    1.02
    glers
    0.99
    uild
    0.98
    Act Density 0.021%

    No Known Activations