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

    Neuronpedia

    INDEX
    Explanations

    occurrences of respectful titles and phrases in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IndentedString
    -0.64
    σθαι
    -0.62
    ItemBackground
    -0.59
    featureID
    -0.59
    клопе
    -0.57
     EconPapers
    -0.56
     QtWidgets
    -0.55
    tvguidetime
    -0.55
     betweenstory
    -0.54
    TemporalType
    -0.54
    POSITIVE LOGITS
     apă
    0.54
    ,'\
    0.49
     NSCoder
    0.47
     convertView
    0.46
     postIndex
    0.45
     AssemblyTitle
    0.45
     areia
    0.43
     uLocal
    0.42
    ']."
    0.42
    __).
    0.42
    Act Density 0.060%

    No Known Activations