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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences ending with punctuation followed by a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    concluding words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.88
     himſelf
    -0.88
     itſelf
    -0.82
    ^(@)
    -0.81
     themſelves
    -0.76
    ſelf
    -0.76
     Majefty
    -0.70
    oredCriteria
    -0.70
     Theſe
    -0.70
     Efq
    -0.69
    POSITIVE LOGITS
     therefore
    2.62
     Therefore
    2.35
    Therefore
    2.29
    therefore
    2.15
     hence
    2.08
     поэтому
    2.05
    Поэтому
    2.00
     donc
    1.92
     Hence
    1.88
     Поэтому
    1.84
    Act Density 0.594%

    No Known Activations