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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to quality and texture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    friends
    -0.89
    laws
    -0.84
    aunts
    -0.78
    rules
    -0.75
    forums
    -0.74
    ources
    -0.73
    hops
    -0.73
    andals
    -0.72
     Trees
    -0.72
    posts
    -0.72
    POSITIVE LOGITS
     outcome
    0.97
     dose
    0.94
     impression
    0.92
     amount
    0.91
     foothold
    0.90
     effect
    0.88
     advantage
    0.88
     approximation
    0.87
     atmosphere
    0.87
     edge
    0.87
    Act Density 0.157%

    No Known Activations