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

    Neuronpedia

    INDEX
    Explanations

    terms related to circumventing rules or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.17
    utar
    -0.16
    scape
    -0.15
    zilla
    -0.15
    Ùĩار
    -0.14
    ilitation
    -0.14
    itar
    -0.14
    jar
    -0.14
    ayout
    -0.14
    ought
    -0.14
    POSITIVE LOGITS
    vented
    0.26
    stantial
    0.25
    venting
    0.25
    vention
    0.23
    vent
    0.22
    fer
    0.21
    stances
    0.20
     circum
    0.20
    ference
    0.20
    amb
    0.19
    Act Density 0.004%

    No Known Activations