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

    Neuronpedia

    INDEX
    Explanations

    verbs related to processing or manipulating information

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to processes and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dracula
    -0.68
     Cah
    -0.66
    BuyableInstoreAndOnline
    -0.60
     Commissioners
    -0.60
    our
    -0.59
     Confeder
    -0.58
     Horton
    -0.57
     Suffolk
    -0.57
     Phi
    -0.57
     Chung
    -0.56
    POSITIVE LOGITS
     easily
    1.23
     cheaply
    1.19
     anytime
    1.17
     safely
    1.16
     anywhere
    1.14
     anonymously
    1.10
     remotely
    1.02
     securely
    1.01
     indefinitely
    0.97
     freely
    0.96
    Act Density 0.175%

    No Known Activations