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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numbers, particularly "four" and "five"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tch
    -0.78
    fw
    -0.75
    Dialogue
    -0.65
     Collider
    -0.64
     srfAttach
    -0.63
     Advertisement
    -0.62
    haps
    -0.62
    verty
    -0.61
    volt
    -0.60
    agine
    -0.60
    POSITIVE LOGITS
     sides
    0.98
     phases
    0.96
     sexes
    0.90
     facets
    0.90
    ieth
    0.88
     genders
    0.83
     halves
    0.80
     quarters
    0.79
     branches
    0.78
     corners
    0.77
    Act Density 0.029%

    No Known Activations