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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations related to differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     curd
    -0.72
     gynhyrchwyd
    -0.69
     AssemblyCulture
    -0.65
    KeyId
    -0.63
     Бю
    -0.62
    easter
    -0.62
     pref
    -0.61
    วก
    -0.61
     referenties
    -0.61
     kew
    -0.60
    POSITIVE LOGITS
    Delta
    1.21
     triangles
    1.13
     triangle
    1.12
     Triangle
    1.05
    Triangle
    1.02
     Δ
    1.01
     Delta
    1.00
    triangle
    0.99
    Δ
    0.93
     ∆
    0.91
    Act Density 0.081%

    No Known Activations