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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of someone making, earns money, or doing a job

    oai_token-act-pair · gpt-3.5-turbo

    actions related to creating or producing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.72
    assis
    -0.69
    heter
    -0.68
    hood
    -0.68
    Mania
    -0.68
    stration
    -0.64
    SPONSORED
    -0.63
     Niet
    -0.62
    Fram
    -0.60
    agogue
    -0.60
    POSITIVE LOGITS
     mistakes
    1.10
     money
    1.08
     decisions
    1.05
     sure
    1.02
     pilgr
    1.00
     strides
    0.99
     sacrifices
    0.95
     documentaries
    0.92
     noises
    0.92
    hift
    0.91
    Act Density 0.121%

    No Known Activations