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

    Neuronpedia

    INDEX
    Explanations

    recurring themes or trends in societal behavior and norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ****************************************************************************
    -0.16
    uled
    -0.15
    ories
    -0.15
    iangle
    -0.15
    enburg
    -0.15
    RICT
    -0.14
    ouro
    -0.14
     interes
    -0.14
     interest
    -0.14
    еÑĢов
    -0.13
    POSITIVE LOGITS
     normal
    0.33
     norm
    0.29
     NORMAL
    0.29
    -normal
    0.29
    normal
    0.28
     routine
    0.28
     Normal
    0.28
     ноÑĢм
    0.28
     part
    0.27
     normalize
    0.26
    Act Density 0.246%

    No Known Activations