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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their associated structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fights
    -0.76
    apo
    -0.75
    Enlarge
    -0.74
    alore
    -0.73
    EStreamFrame
    -0.72
    estate
    -0.70
    papers
    -0.70
    igi
    -0.69
    DragonMagazine
    -0.69
    kef
    -0.69
    POSITIVE LOGITS
     Valiant
    0.77
     Valkyrie
    0.70
     Prototype
    0.68
     Horde
    0.66
     Brotherhood
    0.66
     Rogue
    0.66
     Liberty
    0.66
     Rim
    0.63
     Concord
    0.63
     Weir
    0.62
    Act Density 0.102%

    No Known Activations