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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or organizational programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.72
     dilig
    -0.71
    pick
    -0.69
     humidity
    -0.67
    picking
    -0.64
     IMAGES
    -0.64
    xious
    -0.63
    ModLoader
    -0.63
    ãĥ´
    -0.62
    Boss
    -0.61
    POSITIVE LOGITS
    mable
    1.75
    matic
    1.43
    matically
    1.42
    mers
    0.94
     Gutenberg
    0.88
     instituted
    0.85
    atically
    0.82
    atical
    0.81
    mes
    0.81
    eers
    0.80
    Act Density 0.035%

    No Known Activations