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

    Neuronpedia

    INDEX
    Explanations

    references to codes and identifiers related to security vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑī
    -0.19
    reet
    -0.15
    eatures
    -0.15
    riad
    -0.14
    Persistent
    -0.14
    Brief
    -0.14
    orr
    -0.14
    ži
    -0.14
    errick
    -0.14
    atter
    -0.13
    POSITIVE LOGITS
    ocab
    0.16
    ARGV
    0.15
    urgeon
    0.15
    _CBC
    0.15
    .weixin
    0.15
    ÙĦÙī
    0.14
    _AUX
    0.14
    /cop
    0.14
    ylim
    0.14
     puss
    0.14
    Act Density 0.083%

    No Known Activations