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

    Neuronpedia

    INDEX
    Explanations

    information related to recent actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases indicating recent actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.88
    SPONSORED
    -0.82
     ãĤµ
    -0.79
    omal
    -0.71
    amen
    -0.69
    later
    -0.69
    goal
    -0.69
    mens
    -0.68
    often
    -0.67
    pattern
    -0.66
    POSITIVE LOGITS
    WIND
    0.80
     kindergarten
    0.76
     RELE
    0.76
    daq
    0.74
    DAQ
    0.74
     YORK
    0.67
    LEASE
    0.67
    çIJ
    0.66
    USS
    0.62
    CLASSIFIED
    0.61
    Act Density 0.100%

    No Known Activations