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

    Neuronpedia

    INDEX
    Explanations

    words related to decay or decline

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rot" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.74
     EntityItem
    -0.72
    rahim
    -0.67
    omething
    -0.64
    inez
    -0.61
     Purchase
    -0.59
     Acquisition
    -0.58
     regards
    -0.58
     DRAG
    -0.58
     charism
    -0.58
    POSITIVE LOGITS
    unda
    1.38
    ational
    1.28
    ations
    1.24
    oscope
    1.11
    atory
    1.00
    omon
    0.97
    osc
    0.95
    und
    0.94
    ife
    0.92
    ary
    0.89
    Act Density 0.040%

    No Known Activations