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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "be" in different contexts or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AGE
    -0.16
    inary
    -0.15
     Wage
    -0.15
    age
    -0.15
    omatic
    -0.14
    ãĤ·ãĥ§ãĥ³
    -0.14
    -height
    -0.14
    cession
    -0.13
    iem
    -0.13
    entials
    -0.13
    POSITIVE LOGITS
    autiful
    0.20
    emoc
    0.19
    emoth
    0.17
    ause
    0.17
    oming
    0.17
    emo
    0.16
    ween
    0.16
    ewolf
    0.16
    ilder
    0.15
    OND
    0.15
    Act Density 0.016%

    No Known Activations