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

    Neuronpedia

    INDEX
    Explanations

    technical terms and procedures such as methods, processes, and tools

    oai_token-act-pair · gpt-3.5-turbo

    methods and techniques related to processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.65
    Wonder
    -0.64
     Wolver
    -0.63
     Wolves
    -0.62
     hadn
    -0.61
    Suddenly
    -0.61
    Had
    -0.61
    court
    -0.59
     Gork
    -0.59
    Hours
    -0.59
    POSITIVE LOGITS
     commonly
    0.85
    igmatic
    0.85
    yip
    0.82
    tymology
    0.79
     simplest
    0.79
    aceae
    0.79
     facult
    0.78
     Definition
    0.77
     easiest
    0.76
    common
    0.76
    Act Density 0.789%

    No Known Activations