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

    Neuronpedia

    INDEX
    Explanations

    terms related to forceful actions or compression

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ram" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Johns
    -0.72
     Vald
    -0.69
     Knight
    -0.67
    NC
    -0.67
     Marqu
    -0.66
     Darkness
    -0.66
     Clo
    -0.65
    KI
    -0.65
     Jenner
    -0.65
     Wid
    -0.65
    POSITIVE LOGITS
     ram
    1.26
    ming
    1.11
    dump
    1.03
    disk
    0.98
    irez
    0.97
    pling
    0.90
    rod
    0.90
    bling
    0.86
    ram
    0.82
    pled
    0.80
    Act Density 0.008%

    No Known Activations