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

    Neuronpedia

    INDEX
    Explanations

    statements involving the word "it" in various contexts

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

    Follows the word "was," "is," or "'s"

    np_acts-logits-general · gemini-2.0-flash

    was a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.73
    ]")]
    -0.70
     himſelf
    -0.68
     themſelves
    -0.67
    InstanceState
    -0.65
     whoſe
    -0.63
    httphttps
    -0.62
     raiſ
    -0.61
     poichè
    -0.60
     Majefty
    -0.59
    POSITIVE LOGITS
     a
    0.80
     the
    0.69
     an
    0.64
     good
    0.62
    retts
    0.62
     pure
    0.62
     all
    0.61
    ETIME
    0.59
     time
    0.59
    EOUS
    0.59
    Act Density 0.215%

    No Known Activations