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

    Neuronpedia

    INDEX
    Explanations

    programming-related code structures

    oai_token-act-pair · gpt-3.5-turbo

    recurring themes of missed chances or unresolved situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undet
    -0.89
     ultr
    -0.79
     qualified
    -0.78
     undisclosed
    -0.78
     brid
    -0.77
     mutually
    -0.77
     displacement
    -0.77
     intended
    -0.76
     payroll
    -0.75
     dubbed
    -0.75
    POSITIVE LOGITS
    Anyway
    2.08
    Advertisement
    1.62
    Advertisements
    1.52
    So
    1.52
    But
    1.50
    Maybe
    1.49
    Because
    1.46
    Luckily
    1.46
    Instead
    1.45
    Secondly
    1.45
    Act Density 0.483%

    No Known Activations