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

    Neuronpedia

    INDEX
    Explanations

    specific locations or objects in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical locations and contexts in various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogens
    -0.68
    someone
    -0.62
    ones
    -0.61
     Serving
    -0.61
     Topic
    -0.60
    pires
    -0.58
    fitting
    -0.57
    racuse
    -0.57
    signed
    -0.57
    Subject
    -0.57
    POSITIVE LOGITS
     spree
    0.85
    eworld
    0.76
     woes
    0.74
     rampage
    0.66
     selves
    0.66
    ãĥķãĤ©
    0.65
    ouf
    0.65
    azeera
    0.64
     respectively
    0.64
    atical
    0.64
    Act Density 0.285%

    No Known Activations