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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and specific phrases indicating user intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensement
    -0.59
    ftagPool
    -0.52
     AssemblyCompany
    -0.47
    rapie
    -0.45
    RenderAtEndOf
    -0.44
    assertNotNull
    -0.44
    umeric
    -0.44
    WriteAttribute
    -0.42
    lapsingToolbar
    -0.42
    čin
    -0.41
    POSITIVE LOGITS
     want
    2.48
     wants
    2.31
     wanted
    2.19
    want
    2.15
     wanting
    2.10
     Want
    2.08
     desire
    2.00
     desired
    1.97
    Want
    1.91
    wanted
    1.90
    Act Density 0.877%

    No Known Activations