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

    Neuronpedia

    INDEX
    Explanations

    origins or sources of things

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "origin" or beginnings of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicop
    -0.74
    eneg
    -0.73
    Agg
    -0.71
    ĵĺ
    -0.71
     pestic
    -0.69
    uster
    -0.65
    usters
    -0.65
     Patton
    -0.62
    channelAvailability
    -0.60
     lapt
    -0.59
    POSITIVE LOGITS
    ators
    1.14
    ator
    1.09
    ates
    1.02
    itious
    0.88
     myth
    0.86
     myths
    0.85
    waters
    0.85
     story
    0.81
     tale
    0.78
    uating
    0.77
    Act Density 0.039%

    No Known Activations