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

    Neuronpedia

    INDEX
    Explanations

    references to babies and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CWE
    -0.82
    ]').
    -0.73
    }`)
    -0.73
    }`
    -0.71
    }`).
    -0.69
    "]').
    -0.67
    esgue
    -0.67
    YourGuide
    -0.66
     prior
    -0.65
    ]**
    -0.64
    POSITIVE LOGITS
     babies
    1.85
     baby
    1.79
     Baby
    1.74
     BABY
    1.71
    baby
    1.70
    Baby
    1.70
    BABY
    1.66
    babies
    1.54
     Babies
    1.54
    Babies
    1.44
    Act Density 0.033%

    No Known Activations