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

    Neuronpedia

    INDEX
    Explanations

    references to baths or bathing-related concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    談社
    -0.83
     verily
    -0.83
    Derrick
    -0.79
    FontOfSize
    -0.79
    postolic
    -0.79
    JCheckBox
    -0.78
    rostis
    -0.77
    BoxShadow
    -0.77
    multicolumn
    -0.77
     ExecuteAsync
    -0.76
    POSITIVE LOGITS
     Bath
    1.75
     bath
    1.74
    Bath
    1.70
     BATH
    1.55
     baths
    1.51
    bath
    1.30
     Baths
    1.22
    BATH
    1.22
     bathtub
    1.13
     bathing
    1.05
    Act Density 0.011%

    No Known Activations