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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and terminology used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dio
    -0.18
     thr
    -0.16
     rock
    -0.15
    ulen
    -0.15
    474
    -0.15
     hang
    -0.15
    wb
    -0.15
     Rock
    -0.15
    WB
    -0.15
    GM
    -0.14
    POSITIVE LOGITS
     Pain
    0.27
    integr
    0.20
     sol
    0.20
     Integr
    0.19
    çĹĽ
    0.19
    pain
    0.19
     integr
    0.18
    ollen
    0.18
    sol
    0.18
     Hiro
    0.17
    Act Density 0.049%

    No Known Activations