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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" and related prepositions or conjunctions

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

    comment voir, comment aller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    -0.43
     /
    -0.41
     purpoſe
    -0.40
     ſtate
    -0.39
     calculées
    -0.36
     jä
    -0.35
    /-
    -0.35
     or
    -0.34
     souri
    -0.34
     extérieure
    -0.34
    POSITIVE LOGITS
     να
    0.71
    ]]:
    0.68
     dass
    0.68
    ;";
    0.66
     ότι
    0.66
     att
    0.65
    "],
    0.64
     μην
    0.64
    dass
    0.63
     أن
    0.62
    Act Density 0.001%

    No Known Activations