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

    Neuronpedia

    INDEX
    Explanations

    words related to preservation or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -1.07
    OGND
    -0.80
     Pandey
    -0.72
    modelName
    -0.72
     Adamson
    -0.71
    reportWebVitals
    -0.71
    er
    -0.70
    Personensuche
    -0.70
    digm
    -0.69
     Jacobsen
    -0.69
    POSITIVE LOGITS
     keep
    2.07
    keep
    1.95
     Keep
    1.91
     KEEP
    1.91
    Keeps
    1.86
     kept
    1.85
    Keep
    1.85
    KEEP
    1.85
     keeps
    1.84
     Keeping
    1.73
    Act Density 0.040%

    No Known Activations