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

    Neuronpedia

    INDEX
    Explanations

    names of individuals in political or diplomatic contexts

    oai_token-act-pair · gpt-3.5-turbo

    the use of the article "A" at the beginning of phrases or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IPM
    -0.64
    Finish
    -0.61
    Ö
    -0.60
     Adin
    -0.60
    zx
    -0.60
    antry
    -0.59
    Scot
    -0.59
    arsity
    -0.58
    Own
    -0.58
     Orient
    -0.57
    POSITIVE LOGITS
    cknowled
    1.68
    cknow
    1.33
    verages
    1.19
    lyss
    0.99
    uctions
    0.97
     spokesperson
    0.97
    esthetic
    0.94
     spokeswoman
    0.93
     downside
    0.90
    chieve
    0.90
    Act Density 0.142%

    No Known Activations