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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "probably" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    finder
    -0.16
    men
    -0.16
    iard
    -0.15
     sanki
    -0.15
    оÑĥ
    -0.15
    aphore
    -0.14
    ORE
    -0.14
    869
    -0.14
    odate
    -0.14
    -Men
    -0.14
    POSITIVE LOGITS
    hood
    0.16
    /pro
    0.16
     ÙĬÙĥÙĪÙĨ
    0.15
    aked
    0.15
    -ÑĤаки
    0.14
    Forgery
    0.14
    /security
    0.14
    mente
    0.14
    IRR
    0.14
    çİĩ
    0.14
    Act Density 0.057%

    No Known Activations