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

    Neuronpedia

    INDEX
    Explanations

    words related to physical catastrophes

    oai_token-act-pair · gpt-3.5-turbo

    consequences and events related to disasters or catastrophic situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cheong
    -0.65
    pei
    -0.61
    pton
    -0.60
    hov
    -0.59
    backer
    -0.58
    pointers
    -0.58
    pheus
    -0.58
     Skinner
    -0.58
    kson
    -0.57
    ples
    -0.57
    POSITIVE LOGITS
    rophe
    1.61
    rophic
    1.47
    roph
    1.11
    asia
    1.07
    ruct
    1.05
    efully
    1.04
    rop
    1.01
    acia
    0.99
    igmat
    0.99
    odon
    0.99
    Act Density 0.047%

    No Known Activations