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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a sense of obviousness or highlight undeniable truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ApplicationContext
    -0.16
    ġ
    -0.14
    frey
    -0.14
    OTS
    -0.14
    enz
    -0.14
    bench
    -0.13
    odelist
    -0.13
    leetcode
    -0.13
    getManager
    -0.13
    getExtension
    -0.13
    POSITIVE LOGITS
    eld
    0.16
    Hdr
    0.16
     cand
    0.15
    ensi
    0.15
    isel
    0.15
    ebo
    0.14
    iscal
    0.14
    گاÙĨ
    0.14
     cust
    0.13
     commons
    0.13
    Act Density 0.165%

    No Known Activations