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

    Neuronpedia

    INDEX
    Explanations

    both numerical expressions and indicative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CES
    -0.17
     trÃŃ
    -0.16
     MACHINE
    -0.16
     kla
    -0.15
    ces
    -0.15
    ahn
    -0.15
     CURLOPT
    -0.15
    rance
    -0.15
     Baths
    -0.15
    ugins
    -0.14
    POSITIVE LOGITS
     fine
    0.14
    моÑĤ
    0.14
    isphere
    0.14
    ria
    0.14
     Nano
    0.14
     required
    0.14
     Holly
    0.14
    cheng
    0.14
    &id
    0.14
    ffen
    0.14
    Act Density 0.062%

    No Known Activations