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

    Neuronpedia

    INDEX
    Explanations

    words relating to enhancement, improvement, or boosting in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enhancement or improving conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gamer
    -0.77
    geist
    -0.70
    LAB
    -0.67
     Mistress
    -0.64
     Blow
    -0.63
     Phant
    -0.62
     Fiscal
    -0.62
     externalToEVAOnly
    -0.62
     Fired
    -0.62
     Sakuya
    -0.62
    POSITIVE LOGITS
    anced
    1.44
    ancing
    1.16
    urst
    1.02
    ogh
    0.93
    ishment
    0.92
    orse
    0.92
    obbies
    0.91
    atche
    0.91
    inkle
    0.91
    enh
    0.88
    Act Density 0.020%

    No Known Activations