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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of quantities or numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seat
    -0.77
     Frontier
    -0.69
    inates
    -0.66
     cradle
    -0.64
    asts
    -0.60
    aldi
    -0.60
     caste
    -0.59
    inating
    -0.59
    Blade
    -0.59
    inant
    -0.58
    POSITIVE LOGITS
     amounts
    1.01
     amount
    0.97
    ngth
    0.92
    pour
    0.84
     payable
    0.78
     quantities
    0.75
    encies
    0.74
    ucha
    0.72
    entially
    0.71
    ume
    0.71
    Act Density 0.031%

    No Known Activations