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

    Neuronpedia

    INDEX
    Explanations

    references to security vulnerabilities and issues in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mam
    -0.16
    ennon
    -0.15
    exterity
    -0.15
    odyn
    -0.15
    (Throwable
    -0.14
    zes
    -0.14
    été
    -0.14
    leich
    -0.14
    .assertj
    -0.13
    æ´ª
    -0.13
    POSITIVE LOGITS
     third
    0.21
    third
    0.19
     THIRD
    0.19
    Third
    0.19
     Third
    0.18
     chrome
    0.17
    è°·
    0.16
     absl
    0.16
    ina
    0.15
    Chrome
    0.15
    Act Density 0.026%

    No Known Activations