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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating transitions, changes, or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ju
    -0.15
    ajan
    -0.15
    ZY
    -0.14
    rescia
    -0.14
    ContentLoaded
    -0.14
    ovah
    -0.14
     sunk
    -0.14
     shelves
    -0.14
    ju
    -0.14
     zost
    -0.13
    POSITIVE LOGITS
    defer
    0.18
     makin
    0.16
    ship
    0.16
    ToBounds
    0.16
    âĢŀP
    0.15
    ipel
    0.15
     Clearance
    0.15
     clearance
    0.15
     bordel
    0.15
    ãĥªãĤ¢
    0.15
    Act Density 0.020%

    No Known Activations