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

    Neuronpedia

    INDEX
    Explanations

    expressions related to game mechanics involving balance and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stakes
    -0.16
    sono
    -0.15
    ikel
    -0.15
    aro
    -0.15
    itura
    -0.14
    umper
    -0.14
    record
    -0.14
    croft
    -0.14
    jur
    -0.14
    enos
    -0.13
    POSITIVE LOGITS
    ubar
    0.15
    ircuit
    0.15
    çŃĸ
    0.14
    YPD
    0.14
    UED
    0.14
     Early
    0.14
    زÙĬز
    0.14
    à¹Ģà¸Ļ
    0.14
    avad
    0.14
     ner
    0.13
    Act Density 0.130%

    No Known Activations