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

    Neuronpedia

    INDEX
    Explanations

    words related to shaping or influencing something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "shaping" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upon
    -0.70
     Mub
    -0.68
    nea
    -0.65
    bs
    -0.65
     Journal
    -0.65
     Ps
    -0.64
    ope
    -0.64
    UTERS
    -0.62
     Defense
    -0.62
    mon
    -0.61
    POSITIVE LOGITS
     shaping
    1.21
    eering
    1.09
     tremend
    0.99
     streng
    0.98
    shape
    0.88
     adolesc
    0.85
    ãĤ¼ãĤ¦ãĤ¹
    0.83
     shapes
    0.83
    urated
    0.79
    mble
    0.79
    Act Density 0.005%

    No Known Activations