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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their contents, indicating discussions around contrasts or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.77
    WriteTagHelper
    -0.67
    iastes
    -0.65
    openzeppelin
    -0.64
    دانشنامهٔ
    -0.61
    marshaller
    -0.61
    ⓧ
    -0.61
    windowFixed
    -0.60
     SwitchCompat
    -0.60
     Roskov
    -0.60
    POSITIVE LOGITS
     indeed
    0.64
     albeit
    0.59
    urunan
    0.54
     perhaps
    0.52
     decidedly
    0.51
     البته
    0.51
    NgModule
    0.49
     frankly
    0.49
     sometimes
    0.48
     importantly
    0.48
    Act Density 0.162%

    No Known Activations