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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hands-on activities or craftsmanship

    oai_token-act-pair · gpt-3.5-turbo

    references to processes or actions that involve crafting or handwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    factor
    -0.68
    STER
    -0.67
    Ĥİ
    -0.67
    iatus
    -0.63
    rary
    -0.63
     reven
    -0.62
     bowel
    -0.62
     Lowell
    -0.62
    uct
    -0.62
    antics
    -0.61
    POSITIVE LOGITS
     steering
    0.76
     wielded
    0.71
    picked
    0.70
    cific
    0.67
    ggles
    0.66
    stretched
    0.63
    eret
    0.63
    forward
    0.62
    ricks
    0.61
    prints
    0.60
    Act Density 0.107%

    No Known Activations