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

    Neuronpedia

    INDEX
    Explanations

    references to publications or speeches and their associated dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portal
    -0.07
    оÑĢоз
    -0.07
     завеÑĢ
    -0.07
    lify
    -0.07
    é»
    -0.06
    ulumi
    -0.06
    ilan
    -0.06
    stances
    -0.06
    รม
    -0.06
    _SAFE
    -0.06
    POSITIVE LOGITS
     his
    0.09
     jego
    0.08
     zijn
    0.07
     seinen
    0.07
     ãĢĬ
    0.07
     suas
    0.07
     jeho
    0.07
     seu
    0.07
     его
    0.06
    ä»ĸçļĦ
    0.06
    Act Density 0.026%

    No Known Activations