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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a rising trend or growing significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.17
     progression
    -0.16
    ChangeListener
    -0.15
    kus
    -0.15
    anson
    -0.15
    uri
    -0.15
    تاب
    -0.15
    aign
    -0.14
    InputChange
    -0.14
    çªģçĦ¶
    -0.14
    POSITIVE LOGITS
     increasingly
    0.22
     becoming
    0.22
    ly
    0.19
    è¶Ĭ
    0.19
     è¶
    0.18
     become
    0.16
     Importance
    0.15
     importance
    0.15
    ening
    0.15
    /gtest
    0.15
    Act Density 0.070%

    No Known Activations