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

    Neuronpedia

    INDEX
    Explanations

    words related to institutions/organizations and their initiatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of organizational structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evils
    -0.78
     sins
    -0.71
     Tsukuyomi
    -0.67
    utenberg
    -0.64
     Flavoring
    -0.63
     Incarn
    -0.62
     shocks
    -0.61
     disappoint
    -0.60
     Realms
    -0.60
     extremes
    -0.60
    POSITIVE LOGITS
     dedicated
    1.12
     devoted
    0.91
    matic
    0.87
     called
    0.86
     documenting
    0.82
     specializing
    0.82
    staking
    0.81
     whereby
    0.81
     staffed
    0.80
     dubbed
    0.77
    Act Density 0.498%

    No Known Activations