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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media interactions and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    okane
    -0.15
    CLUSIVE
    -0.14
    ohl
    -0.14
    ebek
    -0.14
    mamak
    -0.14
    assen
    -0.14
     gent
    -0.13
    ød
    -0.13
     buzzing
    -0.13
    Acts
    -0.13
    POSITIVE LOGITS
    agli
    0.16
     experimental
    0.16
     Memo
    0.15
     Experimental
    0.14
     feature
    0.13
    743
    0.13
     extensions
    0.13
    WindowSize
    0.13
    erton
    0.13
    ilton
    0.13
    Act Density 0.089%

    No Known Activations