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

    Neuronpedia

    INDEX
    Explanations

    elements related to decision-making, influence, and agency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ƚ
    -0.65
     gynhyrchwyd
    -0.62
    PreferredItem
    -0.61
     ✭✭
    -0.61
     препратки
    -0.60
    ✭✭
    -0.59
    Referencies
    -0.58
     crdi
    -0.55
    лтамалар
    -0.55
    món
    -0.55
    POSITIVE LOGITS
     she
    1.05
     her
    1.02
     oneself
    0.94
     their
    0.91
    She
    0.90
    Their
    0.90
     Their
    0.86
    she
    0.85
    their
    0.84
     shes
    0.83
    Act Density 0.541%

    No Known Activations