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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or brand names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or brand names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    piring
    -0.64
    oling
    -0.64
     Monk
    -0.62
    yth
    -0.62
     Brett
    -0.62
    olated
    -0.61
    nee
    -0.60
    nard
    -0.59
    older
    -0.57
    odan
    -0.57
    POSITIVE LOGITS
     shareholders
    0.95
     Holdings
    0.84
     employs
    0.84
     Stores
    0.83
     Ltd
    0.83
     executives
    0.83
     subsidiaries
    0.82
     CEO
    0.82
     headquarters
    0.81
     affiliates
    0.79
    Act Density 0.240%

    No Known Activations