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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "it" in various contexts

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

    "it" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    it is important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.77
     Efq
    -0.74
     estekak
    -0.74
     Anſ
    -0.70
     pleaſure
    -0.70
     Monfieur
    -0.70
     PicClick
    -0.70
     doubtnut
    -0.69
     ―――――
    -0.67
     raiſ
    -0.66
    POSITIVE LOGITS
     pays
    0.57
     essentiel
    0.57
     important
    0.56
     critical
    0.55
     béné
    0.54
     crucial
    0.51
     pay
    0.50
     imperative
    0.49
     attiva
    0.49
     fontos
    0.48
    Act Density 0.117%

    No Known Activations