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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "technically"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "technically" and its contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horror
    -0.68
     Cities
    -0.68
     Vaj
    -0.67
     Neighbor
    -0.66
     Memories
    -0.66
    cot
    -0.65
     Delhi
    -0.64
     Surge
    -0.64
     Cly
    -0.64
     Sparkle
    -0.64
    POSITIVE LOGITS
     inclined
    0.97
     speaking
    0.87
     minded
    0.82
     correct
    0.80
     proficient
    0.78
    matical
    0.76
     inept
    0.70
     incorrect
    0.69
     inaccurate
    0.69
    ename
    0.69
    Act Density 0.013%

    No Known Activations