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

    Neuronpedia

    INDEX
    Explanations

    references to cyber threats and security vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aft
    -0.15
    FPS
    -0.15
     Murder
    -0.15
    anca
    -0.14
    antine
    -0.14
    unan
    -0.14
    ानत
    -0.14
    esser
    -0.14
    ipple
    -0.14
    arity
    -0.13
    POSITIVE LOGITS
     targeting
    0.23
     Target
    0.20
     target
    0.20
     attack
    0.19
     targets
    0.18
     sophistication
    0.18
    target
    0.18
     Targets
    0.17
    Targets
    0.17
     attacks
    0.17
    Act Density 0.081%

    No Known Activations