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

    Neuronpedia

    INDEX
    Explanations

    words related to reputation and its perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.84
     nahilalakip
    -0.79
     /\.
    -0.74
    contentLoaded
    -0.73
    -0.72
    httphttps
    -0.68
    IUrlHelper
    -0.65
    tagHelperRunner
    -0.62
     AssemblyProduct
    -0.61
    AntiForgeryToken
    -0.60
    POSITIVE LOGITS
     premises
    0.87
     Premises
    0.73
     Barbara
    0.73
     Boolean
    0.72
    Barbara
    0.71
    leſs
    0.69
     boolean
    0.68
    thâu
    0.68
     premise
    0.67
     newspaper
    0.67
    Act Density 0.038%

    No Known Activations