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

    Neuronpedia

    INDEX
    Explanations

    references to employment termination and the reasons behind it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    firing or terminated employment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.41
     equilibr
    -0.37
     equili
    -0.37
     Moll
    -0.37
     Avalon
    -0.36
     yyl
    -0.36
    <_>
    -0.36
    fVar
    -0.35
    Artists
    -0.35
    PropertyGroup
    -0.35
    POSITIVE LOGITS
     desped
    0.54
     expelled
    0.52
     expulsion
    0.50
    EndContext
    0.50
     оригіналу
    0.49
     ejected
    0.48
    المناصب
    0.48
     Konsequ
    0.47
    DeleteCommand
    0.47
     putus
    0.46
    Act Density 0.033%

    No Known Activations