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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "with" used to introduce phrases

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

    With the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.56
    =$?
    -0.56
    rungsseite
    -0.54
    NOPQRST
    -0.50
     Harp
    -0.50
    createNewFile
    -0.50
    URLException
    -0.47
     ujednoznacz
    -0.47
     Caesar
    -0.46
     PSC
    -0.46
    POSITIVE LOGITS
    With
    0.85
     With
    0.73
    WITH
    0.63
    Avec
    0.58
     Avec
    0.57
    Với
    0.56
    with
    0.54
     Với
    0.54
     WITH
    0.52
     Dengan
    0.51
    Act Density 0.023%

    No Known Activations