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

    Neuronpedia

    INDEX
    Explanations

    terms related to transformation and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mit
    -0.15
    itorio
    -0.14
     Ñĥда
    -0.13
    nech
    -0.13
     wieder
    -0.13
    ames
    -0.13
    ãģĭãģ£ãģ¦
    -0.13
    (Collision
    -0.13
    ูม
    -0.13
     resume
    -0.13
    POSITIVE LOGITS
     change
    0.49
     shift
    0.43
     transformation
    0.41
    change
    0.40
     transition
    0.38
     shifts
    0.35
     Change
    0.35
    -change
    0.34
    Change
    0.34
     transformations
    0.34
    Act Density 0.304%

    No Known Activations