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

    Neuronpedia

    INDEX
    Explanations

    financial information and transactions

    oai_token-act-pair · gpt-3.5-turbo

    financial contributions and fundraising activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earch
    -0.57
    selves
    -0.56
     respectively
    -0.55
     unison
    -0.55
    common
    -0.54
    ogether
    -0.54
     collectively
    -0.52
    vironment
    -0.49
    abee
    -0.49
    sylv
    -0.49
    POSITIVE LOGITS
     himself
    1.06
     Himself
    0.77
     his
    0.73
     wife
    0.65
     stint
    0.64
     resign
    0.62
     solo
    0.62
     cameo
    0.61
    itone
    0.61
     girlfriend
    0.60
    Act Density 1.352%

    No Known Activations