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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their conjugations in the context of expressing possibility or necessity

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

    Followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -1.04
    ſelf
    -1.01
     pleaſure
    -0.82
     AssemblyCulture
    -0.81
     greateſt
    -0.79
     Majefty
    -0.78
    Pfalz
    -0.73
    posób
    -0.69
    Brainz
    -0.69
     hennes
    -0.68
    POSITIVE LOGITS
     they
    1.50
     we
    1.36
     he
    1.32
     it
    1.14
     you
    1.13
     они
    1.06
     she
    1.06
     она
    1.04
     он
    0.93
     оно
    0.84
    Act Density 0.061%

    No Known Activations