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

    Neuronpedia

    INDEX
    Explanations

    words related to technology, potentially focusing on encryption, security, and communication devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    esta
    -0.78
    osterone
    -0.74
    é¾įå
    -0.74
     XVI
    -0.73
    istic
    -0.73
    uania
    -0.72
    istical
    -0.72
    ocrats
    -0.70
    icus
    -0.68
    izations
    -0.67
    POSITIVE LOGITS
    llers
    1.04
    ller
    0.93
    lling
    0.92
    lled
    0.88
    lette
    0.88
    senal
    0.84
    fect
    0.84
    rer
    0.83
    llor
    0.83
    aters
    0.83
    Act Density 0.049%

    No Known Activations