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

    Neuronpedia

    INDEX
    Explanations

    terms related to winning or victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olu
    -0.16
    cia
    -0.15
    leh
    -0.14
    AMAGE
    -0.14
    yll
    -0.14
    360
    -0.14
    pace
    -0.14
    luž
    -0.13
     Ñī
    -0.13
    ujet
    -0.13
    POSITIVE LOGITS
    nable
    0.24
    -win
    0.20
    ced
    0.19
    ess
    0.18
    throp
    0.17
    NF
    0.16
    -loss
    0.16
    /win
    0.16
     battles
    0.16
    now
    0.15
    Act Density 0.086%

    No Known Activations