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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "attack"

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

    attack followed by a preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zelve
    -0.51
     GenerationType
    -0.51
    Autoritní
    -0.50
    wele
    -0.50
     kaarangay
    -0.49
     daarvoor
    -0.49
    "}")
    -0.48
     GV
    -0.48
    resizingMask
    -0.48
    #)
    -0.48
    POSITIVE LOGITS
     attack
    2.02
    attack
    1.78
     Attack
    1.73
    Attack
    1.63
     attacks
    1.63
     ATTACK
    1.59
     attacked
    1.38
    ATTACK
    1.38
     ataque
    1.35
    attacks
    1.35
    Act Density 0.008%

    No Known Activations