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

    Neuronpedia

    INDEX
    Explanations

    references to significant personal attributes or qualities of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    personal pronouns and past tense verbs related to personal actions and experiences.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    תודה
    -0.44
     polaire
    -0.43
     berkenaan
    -0.43
    iální
    -0.43
     AssemblyCulture
    -0.42
     uParam
    -0.42
     snippetHide
    -0.41
     Sahne
    -0.41
    ètement
    -0.40
    landet
    -0.40
    POSITIVE LOGITS
     AppCompatTheme
    0.57
     hobbies
    0.53
    ValueStyle
    0.50
    SequentialGroup
    0.49
     loved
    0.46
    readFileSync
    0.46
    pantalones
    0.45
     Hobbies
    0.45
    :✨
    0.43
    AnimationsModule
    0.43
    Act Density 0.006%

    No Known Activations