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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

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

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.60
     bowiem
    -0.53
     ilustracja
    -0.53
    ismet
    -0.52
     męski
    -0.49
     antichi
    -0.49
    __":
    -0.49
     OnTrigger
    -0.48
     Roskov
    -0.48
     kurtka
    -0.47
    POSITIVE LOGITS
    GOTREF
    0.45
     mess
    0.44
     pesky
    0.40
     nakalista
    0.39
     kinda
    0.38
     stuff
    0.37
     darn
    0.37
     ostavi
    0.37
    oa̍t
    0.37
     couple
    0.36
    Act Density 0.116%

    No Known Activations