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

    Neuronpedia

    INDEX
    Explanations

    verbs related to performing actions or duties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.96
     Efq
    -0.84
     houſe
    -0.80
     ſy
    -0.72
     Reſ
    -0.72
     NLR
    -0.72
     Houſe
    -0.72
     stiefel
    -0.71
    PerformLayout
    -0.71
     متعلقه
    -0.71
    POSITIVE LOGITS
     does
    1.22
     do
    1.10
     did
    1.01
     DOES
    0.95
     DID
    0.94
     not
    0.92
     Does
    0.92
    does
    0.86
     indeed
    0.85
    Does
    0.81
    Act Density 0.107%

    No Known Activations