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

    Neuronpedia

    INDEX
    Explanations

    instances of sequential phrases and sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /embed
    -0.14
    hecy
    -0.14
    736
    -0.14
    ãģĦãĤĦ
    -0.14
     ÑĤоже
    -0.13
    ymax
    -0.13
    931
    -0.13
    è¿ĺæĺ¯
    -0.13
    rias
    -0.13
     carrier
    -0.12
    POSITIVE LOGITS
     then
    0.53
     THEN
    0.45
    then
    0.44
     Then
    0.44
    Then
    0.42
    çĦ¶åIJİ
    0.38
     once
    0.37
    THEN
    0.36
    	then
    0.33
     Once
    0.32
    Act Density 0.177%

    No Known Activations