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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and settings configuration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialized services, features, or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.85
    itably
    -0.83
    iannopoulos
    -0.79
    anwhile
    -0.75
    etheless
    -0.71
    olson
    -0.68
    yright
    -0.66
     republican
    -0.65
     laz
    -0.64
    ounter
    -0.64
    POSITIVE LOGITS
     Mode
    1.09
     Definition
    1.04
     Manager
    1.04
     Points
    1.01
     Selection
    1.00
     Methods
    0.98
     Settings
    0.97
     Mechanics
    0.96
     Characters
    0.95
     Builder
    0.94
    Act Density 0.479%

    No Known Activations