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

    Neuronpedia

    INDEX
    Explanations

    words related to weaknesses and vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovsky
    -0.16
    ills
    -0.15
    ater
    -0.15
    ze
    -0.14
     Crane
    -0.14
    olis
    -0.14
    farm
    -0.13
     farm
    -0.13
    xp
    -0.13
    -0.13
    POSITIVE LOGITS
    à¤Ĺल
    0.17
    ATAR
    0.16
    Cascade
    0.15
    eyen
    0.14
    iverz
    0.14
    \OptionsResolver
    0.14
    stdClass
    0.14
    ihar
    0.14
    аниÑĨ
    0.14
    modifiable
    0.14
    Act Density 0.003%

    No Known Activations