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

    Neuronpedia

    INDEX
    Explanations

    phrases related to routine or standard procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concept of business as usual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.59
    xc
    -0.56
    urally
    -0.53
    entimes
    -0.53
     Marshal
    -0.51
     Seas
    -0.50
     Corridor
    -0.49
     descriptions
    -0.49
     perceive
    -0.48
    pedia
    -0.47
    POSITIVE LOGITS
    arb
    0.54
    ij士
    0.53
    adr
    0.52
    aine
    0.51
    relations
    0.51
    seless
    0.48
    anting
    0.47
    rake
    0.47
    aturdays
    0.47
    ADS
    0.47
    Act Density 0.506%

    No Known Activations