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

    Neuronpedia

    INDEX
    Explanations

    variations of a specific word related to identity or being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    968
    -0.15
    RECT
    -0.14
     Mus
    -0.14
    care
    -0.14
    orer
    -0.14
    Mus
    -0.14
     Ner
    -0.13
    ii
    -0.13
     mus
    -0.13
    ib
    -0.13
    POSITIVE LOGITS
    omite
    0.18
    okino
    0.17
    лиÑĤ
    0.16
    omit
    0.15
     Literature
    0.15
     literature
    0.15
    ismic
    0.15
    ystack
    0.15
    licos
    0.15
    ügen
    0.14
    Act Density 0.009%

    No Known Activations