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

    Neuronpedia

    INDEX
    Explanations

    words related to selecting and choosing among options

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to various types of selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wig
    -0.79
    peria
    -0.77
    kos
    -0.74
    mond
    -0.70
    MER
    -0.65
    hur
    -0.65
    olid
    -0.64
    head
    -0.64
    stead
    -0.62
    alone
    -0.62
    POSITIVE LOGITS
    selection
    1.06
     criteria
    0.90
    ivity
    0.89
     selection
    0.86
     selections
    0.85
    axe
    0.84
     Selection
    0.79
    ively
    0.79
    eering
    0.78
    ivities
    0.76
    Act Density 0.024%

    No Known Activations