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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quotes or speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.74
     BrowserModule
    -0.63
    المناصب
    -0.58
    aarrggbb
    -0.58
    flink
    -0.55
    gasse
    -0.54
    сова
    -0.54
    IInterface
    -0.53
    Jährige
    -0.51
    Cyfeiriadau
    -0.51
    POSITIVE LOGITS
     тоже
    0.52
     '{@
    0.49
    andExpect
    0.49
    WriteBarrier
    0.49
     שוליים
    0.49
    culin
    0.48
    也将
    0.47
    champs
    0.46
     devrez
    0.45
     joining
    0.45
    Act Density 0.163%

    No Known Activations