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

    Neuronpedia

    INDEX
    Explanations

    instances where things are being utilized or employed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "used" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hai
    -0.72
     Tale
    -0.71
    gdala
    -0.68
    nesty
    -0.66
    mare
    -0.65
    awk
    -0.65
    COMPLE
    -0.63
    odore
    -0.62
    dom
    -0.61
    bitious
    -0.61
    POSITIVE LOGITS
     sparing
    0.91
    fully
    0.83
     Used
    0.78
     extensively
    0.72
    FUL
    0.72
     interchange
    0.70
     condoms
    0.68
    MSN
    0.68
     wielded
    0.67
     wisely
    0.66
    Act Density 0.053%

    No Known Activations