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

    Neuronpedia

    INDEX
    Explanations

    references to alcohol and its effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricular
    -0.45
    ola
    -0.44
     trigo
    -0.44
     intima
    -0.43
    GGLE
    -0.43
     кише
    -0.43
     worauf
    -0.42
     merav
    -0.42
     propOrder
    -0.41
     szczy
    -0.41
    POSITIVE LOGITS
     alcohol
    1.63
     liquor
    1.57
    alcohol
    1.48
     drugs
    1.46
     drug
    1.43
     Alcohol
    1.42
    Alcohol
    1.39
    drugs
    1.38
     booze
    1.37
     alcoholic
    1.36
    Act Density 2.983%

    No Known Activations