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

    Neuronpedia

    INDEX
    Explanations

    terms related to revenge and retaliation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     MenuView
    -0.64
     pierdas
    -0.62
     jäsen
    -0.61
     Mue
    -0.61
     vescovo
    -0.60
    rabble
    -0.60
    MLE
    -0.58
     проблему
    -0.58
     Bany
    -0.58
     /^[
    -0.57
    POSITIVE LOGITS
     Revenge
    1.18
     revenge
    1.13
    Revenge
    1.09
     vengeance
    1.05
     retaliation
    1.00
    revenge
    0.96
     venge
    0.86
     Vengeance
    0.85
    venge
    0.84
     retali
    0.82
    Act Density 0.004%

    No Known Activations