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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships and connections in context

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

    Following prepositions

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by verbs or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.38
     and
    -0.35
    ,
    -0.35
    yntaxException
    -0.31
    enumi
    -0.29
    WithMany
    -0.28
     descendre
    -0.28
     Aufenthalts
    -0.28
     malheur
    -0.27
    (
    -0.27
    POSITIVE LOGITS
     препратки
    0.82
    ſſung
    0.81
     fashiola
    0.81
    transQ
    0.80
    <unused17>
    0.80
    <unused14>
    0.80
    <unused41>
    0.80
    <unused52>
    0.80
    [@BOS@]
    0.80
    <unused8>
    0.80
    Act Density 0.994%

    No Known Activations