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

    Neuronpedia

    INDEX
    Explanations

    words related to industry and governmental roles

    oai_token-act-pair · gpt-3.5-turbo

    references to industry, particularly in context with health and safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rooms
    -0.85
    illac
    -0.83
    Ü
    -0.78
    itol
    -0.78
    yards
    -0.77
    avers
    -0.77
    halla
    -0.75
    efer
    -0.74
    ¶ħ
    -0.73
    utsche
    -0.73
    POSITIVE LOGITS
    ALLY
    0.93
     Pacers
    0.76
    FP
    0.73
     Lum
    0.69
     Investor
    0.69
    orescence
    0.68
     Gathering
    0.66
     Tend
    0.66
    achi
    0.63
     Flames
    0.63
    Act Density 0.149%

    No Known Activations