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

    Neuronpedia

    INDEX
    Explanations

    the word "rebounds" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to basketball rebounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ce
    -0.77
    cher
    -0.71
    pat
    -0.69
    Tor
    -0.67
    cel
    -0.66
    il
    -0.66
    lex
    -0.65
    lic
    -0.65
    >>
    -0.64
    leg
    -0.64
    POSITIVE LOGITS
     rebounds
    3.72
     rebound
    2.08
     turnovers
    1.31
     bounces
    1.22
     strikeouts
    1.21
     steals
    1.17
     Pistons
    1.11
     Bosh
    1.06
     Lakers
    1.06
    asketball
    1.05
    Act Density 0.012%

    No Known Activations