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

    Neuronpedia

    INDEX
    Explanations

    keywords related to attacks or battles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of attacks in games and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YC
    -0.72
    zl
    -0.72
    essage
    -0.66
    ãĤ©
    -0.66
    inders
    -0.65
    inder
    -0.63
    姫
    -0.62
    theless
    -0.62
    ETA
    -0.62
    milo
    -0.61
    POSITIVE LOGITS
     against
    0.82
    iveness
    0.81
     vector
    0.76
    ivated
    0.74
     attack
    0.73
    attack
    0.73
     attacks
    0.73
    CVE
    0.73
    ivation
    0.73
    oise
    0.72
    Act Density 0.046%

    No Known Activations