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

    Neuronpedia

    INDEX
    Explanations

    words associated with praise or commendation

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

    commend, applaud, spectrometer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createSlice
    -0.45
     flas
    -0.45
    getUrl
    -0.44
    eburger
    -0.44
     irrig
    -0.42
    multer
    -0.42
    Role
    -0.42
    Igles
    -0.41
    Lopez
    -0.41
     partout
    -0.41
    POSITIVE LOGITS
     commend
    1.73
     commended
    1.65
     commendation
    1.36
     commendable
    1.17
    mendation
    0.97
     applaud
    0.91
    mendations
    0.90
     applauded
    0.85
     comm
    0.79
     appla
    0.74
    Act Density 0.004%

    No Known Activations