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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal sentiment and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheduler
    -0.52
     stron
    -0.50
     Stron
    -0.50
    Gott
    -0.50
    stron
    -0.48
    thyst
    -0.48
     compren
    -0.48
     lactation
    -0.47
     formative
    -0.47
    styleable
    -0.46
    POSITIVE LOGITS
     graag
    0.88
     want
    0.78
    \{\\
    0.75
    wants
    0.70
     wants
    0.68
     lenker
    0.67
    want
    0.65
    PreferredItem
    0.64
    didSet
    0.63
    webElementXpaths
    0.62
    Act Density 0.322%

    No Known Activations