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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various forms of collapse or failure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to failures or collapses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     entertained
    -0.85
    omorph
    -0.66
    icons
    -0.63
    ios
    -0.62
    visual
    -0.62
     entert
    -0.61
    orney
    -0.57
    inal
    -0.57
     computed
    -0.57
     reserved
    -0.57
    POSITIVE LOGITS
     prematurely
    1.24
     unexpectedly
    1.22
     mysteriously
    1.19
     abruptly
    1.12
     tragically
    1.08
     miser
    1.07
     catast
    1.03
     horribly
    0.92
     intest
    0.89
     owing
    0.89
    Act Density 0.191%

    No Known Activations