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

    Neuronpedia

    INDEX
    Explanations

    mathematical or statistical constructs related to density and conditional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ComVisible
    -0.52
    BeginContext
    -0.52
    wendi
    -0.52
    antMatchers
    -0.51
     iprot
    -0.51
     keten
    -0.51
     atheism
    -0.49
     IDL
    -0.49
    FieldBuilder
    -0.47
    OptionsMenu
    -0.47
    POSITIVE LOGITS
     primary
    0.65
    primary
    0.57
     prime
    0.56
    StoreMessageInfo
    0.53
     autorytatywna
    0.52
    TKey
    0.52
     target
    0.52
    uginosa
    0.52
     final
    0.51
     inicial
    0.51
    Act Density 0.484%

    No Known Activations