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

    Neuronpedia

    INDEX
    Explanations

    references to enemies and confrontations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lccn
    -0.65
     seguito
    -0.63
     doby
    -0.63
     Birk
    -0.60
     dAtA
    -0.59
    himo
    -0.57
     correndo
    -0.56
    prudence
    -0.56
    ọt
    -0.55
     hendes
    -0.55
    POSITIVE LOGITS
     Enemy
    1.45
     enemy
    1.41
     enemies
    1.33
     Enemies
    1.27
    enemy
    1.17
    Enemy
    1.17
     foes
    1.11
     opponents
    1.10
    enemies
    1.10
    ennemi
    1.07
    Act Density 0.165%

    No Known Activations