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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical or factual information

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating quantities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    few
    -0.83
    ulhu
    -0.69
    heses
    -0.68
    ula
    -0.67
    ĸļ
    -0.67
    zai
    -0.66
    rh
    -0.65
    months
    -0.65
     Unsure
    -0.64
    render
    -0.63
    POSITIVE LOGITS
     material
    0.77
     cargo
    0.74
     extra
    0.68
     goods
    0.68
     accumulated
    0.67
     cumulative
    0.67
     concentrated
    0.67
     airspace
    0.66
     information
    0.64
     insulation
    0.64
    Act Density 0.081%

    No Known Activations