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

    Neuronpedia

    INDEX
    Explanations

    words related to solving difficult problems or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ol" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Battles
    -0.70
     ISS
    -0.68
    éĹ
    -0.67
     Healer
    -0.66
     UFO
    -0.65
     Presidential
    -0.65
    DATA
    -0.65
     Citizen
    -0.65
    ãģ®éŃĶ
    -0.65
    æĿ
    -0.65
    POSITIVE LOGITS
    ipop
    1.25
    ateral
    1.19
    onial
    1.12
    ength
    1.06
    ounge
    1.03
    ivia
    1.02
    oad
    1.01
    adies
    1.01
    okia
    1.00
    phe
    0.97
    Act Density 0.019%

    No Known Activations