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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "maybe" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omer
    -0.17
    sq
    -0.16
    оÑĥ
    -0.16
    ¹Ħ
    -0.15
    ERC
    -0.14
    wang
    -0.14
    ç¶
    -0.14
    swer
    -0.14
    rdf
    -0.14
    âĢŀV
    -0.14
    POSITIVE LOGITS
     even
    0.21
    haps
    0.18
    even
    0.17
    /pro
    0.16
     latter
    0.16
    eyim
    0.16
    fore
    0.15
    eee
    0.15
     даже
    0.14
     someday
    0.14
    Act Density 0.016%

    No Known Activations