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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enhancement or improvement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enhancement or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.77
     Bullets
    -0.73
     externalToEVAOnly
    -0.71
     line
    -0.68
    bryce
    -0.67
    76561
    -0.67
    ãĥ£
    -0.66
     Dome
    -0.66
     arc
    -0.65
    pool
    -0.63
    POSITIVE LOGITS
    anced
    1.96
    ancing
    1.65
    ances
    1.42
    ance
    1.34
    ancers
    1.33
    ancer
    1.23
    ANC
    1.15
    anc
    1.07
    urance
    0.99
    owers
    0.98
    Act Density 0.032%

    No Known Activations