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

    Neuronpedia

    INDEX
    Explanations

    terms related to increases and decreases in metrics, particularly financial or resource-related changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylene
    -0.15
    neh
    -0.15
    ensely
    -0.14
    eli
    -0.14
    ween
    -0.14
    urrent
    -0.14
     ReturnValue
    -0.14
    zcze
    -0.13
     iss
    -0.13
    allen
    -0.13
    POSITIVE LOGITS
     in
    0.26
    /change
    0.17
    åľ¨åľ°
    0.17
     seen
    0.16
    åľ¨
    0.16
     ÏĥÏĦην
    0.16
    conde
    0.16
     Towers
    0.16
    ãĥ¼ãĥ³
    0.16
     în
    0.15
    Act Density 0.137%

    No Known Activations