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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocol
    -0.17
    427
    -0.16
    æĪ¶
    -0.15
    _RB
    -0.15
    éis
    -0.15
    eyen
    -0.15
    _HT
    -0.15
    ApplicationContext
    -0.14
    sto
    -0.14
    û
    -0.14
    POSITIVE LOGITS
    /security
    0.16
    -minded
    0.16
    andre
    0.16
    ron
    0.15
    ÏĥÏĦα
    0.15
    tainment
    0.15
    (fake
    0.14
    ãĥ³ãĥĩ
    0.14
     Bureau
    0.14
    iliar
    0.14
    Act Density 0.020%

    No Known Activations