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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and bureaucratic processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or formal documents and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iott
    -0.80
    OPE
    -0.76
    eday
    -0.75
    elo
    -0.73
    inately
    -0.72
    ifi
    -0.68
    isy
    -0.67
    inite
    -0.67
    otropic
    -0.66
    respond
    -0.66
    POSITIVE LOGITS
     spree
    1.01
    tons
    0.95
    redients
    0.91
     ability
    0.81
     ceremonies
    0.79
     prowess
    0.77
     ceremony
    0.76
     mechanism
    0.73
     techniques
    0.72
    HAM
    0.72
    Act Density 0.323%

    No Known Activations