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

    Neuronpedia

    INDEX
    Explanations

    references to fighting and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]={↵
    -0.16
    itan
    -0.15
    maj
    -0.15
    sson
    -0.14
    ivr
    -0.14
    518
    -0.14
     Vent
    -0.14
    ONGL
    -0.14
    wort
    -0.14
    ISIBLE
    -0.14
    POSITIVE LOGITS
    olland
    0.17
    utow
    0.16
    LN
    0.16
     Glover
    0.15
     Mix
    0.15
    lemn
    0.15
    emax
    0.15
    ecies
    0.14
    allis
    0.14
    attles
    0.14
    Act Density 0.068%

    No Known Activations