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

    Neuronpedia

    INDEX
    Explanations

    specific references to software, protocols, and data structure formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yang
    -0.41
     ModelExpression
    -0.37
     dan
    -0.36
    RegressionTest
    -0.35
     poses
    -0.33
     stets
    -0.33
    sbericht
    -0.32
     uncanny
    -0.32
     shoulder
    -0.32
     carpet
    -0.32
    POSITIVE LOGITS
     pinulongan
    0.64
     ing
    0.57
     queſta
    0.57
    ⤹
    0.53
     lenker
    0.51
     $_"
    0.51
     '.';
    0.50
     ſind
    0.50
    دانشنامهٔ
    0.49
     $_(
    0.49
    Act Density 0.107%

    No Known Activations