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

    Neuronpedia

    INDEX
    Explanations

    patterns of connection and transitions between different stages or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     otherwise
    -0.15
    isan
    -0.15
    ahn
    -0.15
    -0.15
     poll
    -0.15
    yny
    -0.14
    odel
    -0.14
     m
    -0.14
     Poll
    -0.14
    iras
    -0.14
    POSITIVE LOGITS
     then
    0.41
     rá»ĵi
    0.38
     puis
    0.35
     THEN
    0.35
    then
    0.35
    çĦ¶åIJİ
    0.35
     ultimately
    0.34
     Then
    0.32
    Then
    0.31
    THEN
    0.31
    Act Density 0.250%

    No Known Activations