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

    Neuronpedia

    INDEX
    Explanations

    terms related to protection and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SED
    -0.18
     onBackPressed
    -0.16
    ICES
    -0.15
    stract
    -0.15
    LEGRO
    -0.14
    idal
    -0.14
    forth
    -0.14
    ยา
    -0.14
    erer
    -0.14
    olest
    -0.14
    POSITIVE LOGITS
     against
    0.23
    ively
    0.23
    ive
    0.21
     Against
    0.20
    iveness
    0.19
    Against
    0.18
    against
    0.18
    ECT
    0.17
     measures
    0.16
    odiac
    0.16
    Act Density 0.033%

    No Known Activations