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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transformation or evolution

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

    into a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.60
    Hochspringen
    -0.58
     الحره
    -0.57
    ulemon
    -0.50
     незавершена
    -0.48
    AsUp
    -0.47
    :✨
    -0.46
     consultato
    -0.45
    EndContext
    -0.43
     дописавши
    -0.43
    POSITIVE LOGITS
    argout
    0.45
    webElement
    0.44
     informée
    0.43
    rungsseite
    0.41
     entailed
    0.38
    AlterField
    0.37
    uParam
    0.37
     evolved
    0.35
     Daarna
    0.35
     pinulongan
    0.35
    Act Density 0.090%

    No Known Activations