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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate a confirmation or verification process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.61
    ſelf
    -0.57
     Infórmanos
    -0.52
    rawDesc
    -0.51
    parsedMessage
    -0.50
    principalColumn
    -0.50
     utafitiHapana
    -0.48
     houſe
    -0.48
     MenuView
    -0.46
     himſelf
    -0.45
    POSITIVE LOGITS
     brauche
    0.43
    geist
    0.40
    IsContent
    0.39
     Honesty
    0.37
    anneer
    0.35
     Objective
    0.35
     Worth
    0.35
    orex
    0.34
     EconPapers
    0.33
    jective
    0.33
    Act Density 0.174%

    No Known Activations