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

    Neuronpedia

    INDEX
    Explanations

    instances of the keyword "new" in programming-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.15
    oud
    -0.15
    baugh
    -0.15
    ory
    -0.15
    ervo
    -0.14
    imony
    -0.14
    ัà¸Ħร
    -0.14
    ekk
    -0.14
    reu
    -0.14
    cy
    -0.14
    POSITIVE LOGITS
     ones
    0.17
     Ones
    0.16
    phies
    0.16
    ÙĪÙĨا
    0.15
    ko
    0.15
    urnished
    0.15
    brtc
    0.15
    ĥn
    0.14
    pNet
    0.14
    ç°
    0.14
    Act Density 0.011%

    No Known Activations