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

    Neuronpedia

    INDEX
    Explanations

    phrases related to health checks and testing, alongside words associated with community and support activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ityEngine
    -0.18
    otle
    -0.16
    ètre
    -0.16
    etrain
    -0.16
    ifice
    -0.16
    omaly
    -0.15
     ActionTypes
    -0.15
    eree
    -0.15
    iteit
    -0.15
    crop
    -0.15
    POSITIVE LOGITS
    els
    0.29
    utes
    0.29
    ets
    0.29
    olds
    0.28
    ils
    0.28
    ands
    0.28
    ols
    0.28
    als
    0.28
    ths
    0.28
    outs
    0.27
    Act Density 0.646%

    No Known Activations