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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and events related to community service and social impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lately
    -0.26
     nowadays
    -0.21
     recently
    -0.21
     ÑģейÑĩаÑģ
    -0.20
     currently
    -0.20
     hasn
    -0.20
     aren
    -0.20
     earlier
    -0.20
    currently
    -0.19
     always
    -0.19
    POSITIVE LOGITS
     suddenly
    0.25
     became
    0.24
     began
    0.24
     unexpectedly
    0.23
     was
    0.23
     finally
    0.21
     abruptly
    0.21
     begins
    0.20
    unexpected
    0.20
     becomes
    0.19
    Act Density 0.387%

    No Known Activations