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

    Neuronpedia

    INDEX
    Explanations

    terms related to rescue operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rescue and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Belt
    -0.75
     Kane
    -0.72
    heid
    -0.72
    tery
    -0.72
     Smoking
    -0.67
     Dish
    -0.67
     PAX
    -0.67
     Sheen
    -0.67
     Charm
    -0.67
    STEM
    -0.66
    POSITIVE LOGITS
    uers
    1.39
    ues
    1.11
    aled
    1.09
    ategor
    1.08
    outed
    1.06
    ission
    1.04
    oded
    1.01
    aped
    1.01
    uable
    1.01
    hett
    1.00
    Act Density 0.006%

    No Known Activations