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

    Neuronpedia

    INDEX
    Explanations

    words related to person pronouns

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

    Followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by nouns/verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     circ
    -0.47
    awtextra
    -0.47
    recep
    -0.47
     recep
    -0.47
     мәкал
    -0.47
    ôles
    -0.47
    quelize
    -0.46
     Prov
    -0.45
    toprule
    -0.45
     kaynağından
    -0.45
    POSITIVE LOGITS
     berdua
    0.58
    zelf
    0.44
     们
    0.43
     kautta
    0.42
     springfox
    0.40
     aikana
    0.40
     hindurch
    0.40
    langkah
    0.36
     lipat
    0.36
     aikaa
    0.36
    Act Density 0.244%

    No Known Activations