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

    Neuronpedia

    INDEX
    Explanations

    words related to formal and technical processes, particularly those related to finance or governance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of "ization," indicating processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilan
    -0.74
    itness
    -0.72
    ker
    -0.71
    chie
    -0.69
    agher
    -0.69
    soDeliveryDate
    -0.69
    liam
    -0.68
    monds
    -0.64
     spacious
    -0.62
    Lear
    -0.60
    POSITIVE LOGITS
    eering
    0.98
    xual
    0.87
    cember
    0.83
    ktop
    0.82
    ablishment
    0.81
    eers
    0.80
    ality
    0.78
    ization
    0.75
     mismatch
    0.73
    chwitz
    0.72
    Act Density 0.027%

    No Known Activations