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

    Neuronpedia

    INDEX
    Explanations

    words or names related to the concept of "new" or "novelty."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    optera
    -0.19
    thic
    -0.17
    stab
    -0.17
    oke
    -0.16
    pta
    -0.16
    pth
    -0.16
    erin
    -0.15
    achts
    -0.15
    uario
    -0.15
    inel
    -0.15
    POSITIVE LOGITS
    ismatic
    0.20
     nu
    0.17
     Nu
    0.16
    gens
    0.15
    dea
    0.15
    íħĶ
    0.15
     subt
    0.14
    vem
    0.14
     NU
    0.14
    Nu
    0.14
    Act Density 0.034%

    No Known Activations