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

    Neuronpedia

    INDEX
    Explanations

    instances of weak or negative opinions or outcomes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inkel
    -0.07
    .apple
    -0.06
    isti
    -0.06
    ybrid
    -0.06
    statuses
    -0.06
    anzi
    -0.06
    å¼¹
    -0.06
    DeltaTime
    -0.06
    ilot
    -0.06
    าะ
    -0.06
    POSITIVE LOGITS
     intentional
    0.16
     deliberate
    0.13
     intentionally
    0.10
     purpose
    0.09
     intention
    0.09
     intent
    0.08
     conscious
    0.08
    Intent
    0.08
     deliberately
    0.07
     Purpose
    0.07
    Act Density 0.012%

    No Known Activations