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

    Neuronpedia

    INDEX
    Explanations

    phrases related to troubleshooting and resolving technical issues

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

    Hedging adverbs and modal verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verb + auxiliary verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.54
    RenderAtEndOf
    -0.51
    -0.50
    Hochspringen
    -0.50
    testify
    -0.49
    SharedCtor
    -0.49
    GTCX
    -0.47
     defaultstate
    -0.45
    awtextra
    -0.45
    makeText
    -0.45
    POSITIVE LOGITS
     informée
    0.54
     IIRC
    0.46
     IMHO
    0.46
     iirc
    0.43
     yourself
    0.42
     maybe
    0.42
    Filmographie
    0.41
     IMO
    0.40
    wapV
    0.39
     stuff
    0.39
    Act Density 0.707%

    No Known Activations