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

    Neuronpedia

    INDEX
    Explanations

    mentions of the collapse of structures or systems

    oai_token-act-pair · gpt-3.5-turbo

    references to structural failures or collapses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etch
    -0.77
    lean
    -0.77
    qua
    -0.75
    ãĥ£
    -0.67
    cil
    -0.65
    cream
    -0.65
    ju
    -0.64
    Salt
    -0.64
     Pens
    -0.63
    ĭ
    -0.63
    POSITIVE LOGITS
    ulence
    0.97
     miser
    0.80
    ateral
    0.79
    ulent
    0.78
    opian
    0.75
     precip
    0.74
     catast
    0.74
     havoc
    0.73
     dism
    0.71
     jaws
    0.70
    Act Density 0.046%

    No Known Activations