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

    Neuronpedia

    INDEX
    Explanations

    proper names related to politics and film

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stack
    -0.74
    Joined
    -0.66
    athering
    -0.65
     mantle
    -0.65
    vidia
    -0.64
    matter
    -0.61
     behave
    -0.60
    iveness
    -0.59
     guilt
    -0.59
     disk
    -0.58
    POSITIVE LOGITS
    oother
    0.83
    iverpool
    0.82
    akeru
    0.73
    anwhile
    0.70
    BRE
    0.69
    çļ
    0.69
    adesh
    0.68
     bott
    0.68
    OHN
    0.67
    FK
    0.66
    Act Density 0.000%

    No Known Activations