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

    Neuronpedia

    INDEX
    Explanations

    terms related to alcohol use and consumption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]")]
    -0.89
    RegressionTest
    -0.75
     GTS
    -0.75
     beginnetje
    -0.74
    ็จ
    -0.70
     kilomet
    -0.69
    elemField
    -0.69
     siège
    -0.68
     createSprite
    -0.68
    GGLE
    -0.67
    POSITIVE LOGITS
     alcohol
    2.08
     Alcohol
    1.86
    Alcohol
    1.84
     ALCOHOL
    1.83
    alcohol
    1.82
     alcohols
    1.59
     alcoholic
    1.58
     Alkohol
    1.52
     alkohol
    1.51
    COHOL
    1.46
    Act Density 0.079%

    No Known Activations