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

    Neuronpedia

    INDEX
    Explanations

    specific dates and timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imoto
    -0.15
    iz
    -0.15
     пов
    -0.15
     cutting
    -0.15
    ew
    -0.15
    é¼»
    -0.14
    ers
    -0.14
    ulp
    -0.14
    imes
    -0.13
    eo
    -0.13
    POSITIVE LOGITS
    ritten
    0.18
     Leave
    0.17
    //-
    0.17
    venes
    0.16
    	no
    0.16
    Leave
    0.15
     treff
    0.15
     oleh
    0.15
    ohen
    0.15
    OrFail
    0.15
    Act Density 0.023%

    No Known Activations