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

    Neuronpedia

    INDEX
    Explanations

    terms related to dominance and victory, particularly in the context of power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulers
    -0.14
     Bale
    -0.14
     allowances
    -0.14
    ALTH
    -0.14
    392
    -0.13
    alle
    -0.13
    862
    -0.13
    ulist
    -0.13
    éĩı
    -0.13
    ROI
    -0.13
    POSITIVE LOGITS
    ixon
    0.15
     Aires
    0.14
    asper
    0.14
    acock
    0.14
     vad
    0.14
    elm
    0.14
    .ManyToMany
    0.14
     HOH
    0.14
    eny
    0.14
    kas
    0.13
    Act Density 0.015%

    No Known Activations