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

    Neuronpedia

    INDEX
    Explanations

    mentions of organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to various organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.71
    ths
    -0.70
    Tro
    -0.68
    kowski
    -0.66
    ixed
    -0.66
    chie
    -0.65
    gets
    -0.65
    req
    -0.64
    aults
    -0.64
    stroke
    -0.63
    POSITIVE LOGITS
     organization
    1.01
    eers
    1.00
     affili
    0.93
     organisation
    0.85
     organizations
    0.83
    eering
    0.78
    ality
    0.78
     bom
    0.78
    ally
    0.77
    arily
    0.77
    Act Density 0.022%

    No Known Activations