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

    Neuronpedia

    INDEX
    Explanations

    numeric values or dates in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streng
    -0.66
    ioned
    -0.61
     ado
    -0.60
    alogy
    -0.60
    irable
    -0.59
    erred
    -0.59
    natureconservancy
    -0.59
    ustainable
    -0.59
    ALE
    -0.58
    resa
    -0.58
    POSITIVE LOGITS
     1988
    1.26
     1989
    1.26
     1987
    1.25
     1999
    1.24
     1997
    1.24
     1985
    1.23
     2009
    1.22
     1995
    1.22
     1996
    1.22
     1983
    1.22
    Act Density 0.051%

    No Known Activations