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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use of technology or tools

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the use of technology and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    watching
    -0.75
    cffffcc
    -0.74
    occup
    -0.73
    mire
    -0.72
    ridge
    -0.69
    ¯¯¯¯
    -0.68
    Gay
    -0.68
    Brew
    -0.67
    nesty
    -0.67
    Stud
    -0.67
    POSITIVE LOGITS
    fully
    1.00
     borrowed
    0.92
     techniques
    0.91
     sophisticated
    0.87
     recycled
    0.85
     technology
    0.82
     proprietary
    0.80
     algorithms
    0.79
     sparing
    0.79
    stood
    0.76
    Act Density 0.123%

    No Known Activations