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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling the beginning of a list or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reszcie
    -0.65
    %)$
    -0.64
     finally
    -0.61
    "}")
    -0.56
    UnusedPrivate
    -0.56
    солю
    -0.55
    colgroup
    -0.54
     okuyayım
    -0.54
    finally
    -0.52
    chluss
    -0.52
    POSITIVE LOGITS
     responders
    0.85
     impressions
    0.84
     thing
    0.84
     impression
    0.76
    born
    0.76
    fruits
    0.71
     Aid
    0.71
     responder
    0.70
     timers
    0.68
     tiên
    0.68
    Act Density 0.164%

    No Known Activations