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

    Neuronpedia

    INDEX
    Explanations

    words related to strength or intensity

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

    strong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.59
     informée
    -0.58
    EndProject
    -0.55
    PyExc
    -0.54
    iNdEx
    -0.54
    Tikang
    -0.53
     незавершена
    -0.53
    parsedMessage
    -0.52
    GraphicsUnit
    -0.52
    tableFuture
    -0.51
    POSITIVE LOGITS
     strong
    1.84
    strong
    1.82
    Strong
    1.74
     Strong
    1.66
     STRONG
    1.63
    STRONG
    1.60
     strength
    1.55
     stronger
    1.50
     strongest
    1.50
    strength
    1.45
    Act Density 0.064%

    No Known Activations