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

    Neuronpedia

    INDEX
    Explanations

    words related to enhancement or enhancement-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enhancement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gamer
    -0.70
    geist
    -0.68
     Mistress
    -0.67
    ãģ®éŃĶ
    -0.67
     Phant
    -0.66
    76561
    -0.66
     Sakuya
    -0.65
     Fired
    -0.64
     Leilan
    -0.62
    bian
    -0.62
    POSITIVE LOGITS
    anced
    1.49
    ancing
    1.33
    urst
    1.09
    enh
    1.08
    oves
    0.98
    ance
    0.98
    anging
    0.98
    ishment
    0.97
    ocking
    0.95
    orst
    0.94
    Act Density 0.005%

    No Known Activations