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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and parameters in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.92
    ロウィン
    -0.89
     deſſen
    -0.85
     queſta
    -0.84
     témoig
    -0.84
    iſche
    -0.83
     EconPapers
    -0.82
     XNUMX
    -0.82
    niſſe
    -0.82
    <pad>
    -0.82
    POSITIVE LOGITS
     δ
    0.61
    β
    0.60
     β
    0.58
     σ
    0.56
    α
    0.53
     α
    0.52
    χ
    0.50
     γ
    0.49
     θ
    0.49
     χ
    0.48
    Act Density 1.554%

    No Known Activations