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

    Neuronpedia

    INDEX
    Explanations

    phrases related to routine or repetitive actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to frequency of occurrence or regularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.74
     Patriarch
    -0.72
    atories
    -0.71
     Mour
    -0.66
    enic
    -0.65
    erness
    -0.65
     Skies
    -0.63
    asty
    -0.63
     Loch
    -0.62
     Gemini
    -0.61
    POSITIVE LOGITS
     basis
    0.96
     thereafter
    0.93
     occasions
    0.79
     throughout
    0.75
    iatus
    0.73
     contrad
    0.67
     consecut
    0.64
    uation
    0.64
     occas
    0.64
     concurrent
    0.62
    Act Density 0.044%

    No Known Activations