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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreements or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abaj
    -0.16
    ัม
    -0.15
    antas
    -0.14
    af
    -0.14
    LER
    -0.14
    andez
    -0.14
    ARB
    -0.13
     Burns
    -0.13
    AF
    -0.13
    berger
    -0.13
    POSITIVE LOGITS
    .Automation
    0.16
    gement
    0.15
    uzz
    0.15
    uart
    0.14
    ignet
    0.14
    Lik
    0.14
    à¥Ĥद
    0.14
    ration
    0.14
    omy
    0.14
     Interr
    0.14
    Act Density 0.115%

    No Known Activations