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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various forms of attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ав
    -0.63
    AM
    -0.57
    hoga
    -0.56
     թվական
    -0.56
     much
    -0.56
    ImageContext
    -0.53
    {~
    -0.53
     zapatos
    -0.52
    СТВА
    -0.52
     Gln
    -0.52
    POSITIVE LOGITS
     Attack
    1.35
     attacks
    1.33
     ATTACK
    1.33
     attack
    1.33
    Attacks
    1.28
    ATTACK
    1.26
     Attacks
    1.25
    attack
    1.22
    attacks
    1.19
    Attack
    1.07
    Act Density 0.132%

    No Known Activations