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

    Neuronpedia

    INDEX
    Explanations

    sentences that emphasize the word "it" in various contexts

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

    "it" followed by "was" or "is"

    np_acts-logits-general · gemini-2.0-flash

    it was / it is states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theſe
    -0.85
     Theſe
    -0.83
     ſtate
    -0.83
     fubject
    -0.82
     Monfieur
    -0.81
     itſelf
    -0.79
     poffe
    -0.79
    ſelves
    -0.78
     Chriftian
    -0.78
     myſelf
    -0.78
    POSITIVE LOGITS
     
    0.47
    SourceChecksum
    0.46
     freezing
    0.40
    file
    0.40
    мно
    0.40
    penup
    0.40
     اع
    0.39
    freezing
    0.39
     W
    0.39
     hard
    0.39
    Act Density 0.242%

    No Known Activations