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

    Neuronpedia

    INDEX
    Explanations

    terms related to cyber security breaches and hacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.66
     Direction
    -0.65
    antz
    -0.64
    pillar
    -0.64
    Fit
    -0.60
    rio
    -0.59
    sit
    -0.59
    assian
    -0.59
     qualified
    -0.58
    itis
    -0.57
    POSITIVE LOGITS
     by
    0.90
     BY
    0.81
     merciless
    0.74
     electronically
    0.73
     accidentally
    0.72
     violently
    0.71
     unnecessarily
    0.71
     inappropriately
    0.70
     offline
    0.69
     perpetrated
    0.67
    Act Density 0.069%

    No Known Activations