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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to reasoning and explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.49
     sorpresas
    -0.46
    "
    -0.45
     P
    -0.43
    ой
    -0.39
     теперь
    -0.39
     “
    -0.39
     For
    -0.39
    gehen
    -0.38
    ASSERT
    -0.38
    POSITIVE LOGITS
    AndEndTag
    0.90
    IndentedString
    0.89
    PerformLayout
    0.86
    ſelves
    0.82
     myſelf
    0.82
     initComponents
    0.81
     ſtate
    0.81
    ſelf
    0.80
     protoimpl
    0.79
    Enllaces
    0.78
    Act Density 0.414%

    No Known Activations