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

    Neuronpedia

    INDEX
    Explanations

    mentions of soap and soup in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BagConstraints
    -0.68
    πως
    -0.67
     Rover
    -0.65
    ंक
    -0.65
    ="<?=$
    -0.65
    Rover
    -0.62
     Stron
    -0.61
     flé
    -0.61
    #![
    -0.61
    стоин
    -0.61
    POSITIVE LOGITS
     soap
    1.51
     Soap
    1.41
     soaps
    1.31
     SOAP
    1.17
    soap
    1.13
    Soap
    1.13
     opera
    1.07
     Opera
    1.05
    SOAP
    1.05
    Opera
    0.95
    Act Density 0.084%

    No Known Activations