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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "it" and related expressions indicating assumptions or beliefs about subjects

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

    sounds like it might

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     devient
    -0.36
     devenu
    -0.35
     fact
    -0.34
    ofire
    -0.32
     devenus
    -0.32
     devenue
    -0.30
    tonode
    -0.30
    Tämä
    -0.29
    lossary
    -0.29
     himo
    -0.29
    POSITIVE LOGITS
     disambiguazione
    0.71
    ViewInit
    0.57
    fortawesome
    0.53
    Spit
    0.52
    riedenheit
    0.52
     claws
    0.52
    躇
    0.52
    Cav
    0.52
    principalColumn
    0.49
    Hilton
    0.48
    Act Density 0.010%

    No Known Activations