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

    Neuronpedia

    INDEX
    Explanations

    information about government, legislation, and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decomp
    -0.73
     Negro
    -0.73
     paperback
    -0.68
     negro
    -0.65
     regul
    -0.65
     triv
    -0.65
     whiff
    -0.65
     puff
    -0.64
     readings
    -0.64
     reprodu
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.10
    SHIP
    0.90
    taboola
    0.86
    ï¸
    0.85
    ship
    0.84
    VICE
    0.84
    ATH
    0.82
    SHA
    0.81
    IVERS
    0.80
    STEM
    0.79
    Act Density 0.471%

    No Known Activations