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

    Neuronpedia

    INDEX
    Explanations

    words related to placing or positioning something

    oai_token-act-pair · gpt-3.5-turbo

    the word "lay" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.88
    iles
    -0.75
    antly
    -0.68
    iveness
    -0.66
    ernaut
    -0.65
    ractions
    -0.62
    ilation
    -0.62
     Rutherford
    -0.61
     [+
    -0.60
    qua
    -0.59
    POSITIVE LOGITS
     groundwork
    1.08
     siege
    0.94
     bare
    0.85
     dormant
    0.82
     down
    0.78
    ering
    0.77
     foundations
    0.76
    mination
    0.75
     awake
    0.73
    flat
    0.72
    Act Density 0.041%

    No Known Activations