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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or direct speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    saraba
    -0.91
    GEBURTSDATUM
    -0.89
     betweenstory
    -0.89
    principalTable
    -0.85
    GEBURTS
    -0.79
    PerformLayout
    -0.77
     FontWeight
    -0.76
     ویکی‌پدیا
    -0.74
    WarningLevel
    -0.72
    انيف
    -0.70
    POSITIVE LOGITS
     depends
    0.70
    Depends
    0.61
     answer
    0.57
     basically
    0.55
     depende
    0.53
    depends
    0.52
     simply
    0.52
     Depends
    0.49
     básicamente
    0.47
    Basically
    0.47
    Act Density 0.441%

    No Known Activations