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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical destruction or collapse

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.67
    pleasant
    -0.64
     entertained
    -0.64
    tains
    -0.64
    76561
    -0.62
    etch
    -0.62
    POL
    -0.61
     flattering
    -0.60
    alla
    -0.58
    rouse
    -0.58
    POSITIVE LOGITS
     abruptly
    0.92
     mysteriously
    0.91
     miser
    0.91
     prematurely
    0.88
     catast
    0.88
     tragically
    0.86
     amid
    0.81
     intest
    0.80
     unexpectedly
    0.80
     horribly
    0.79
    Act Density 0.267%

    No Known Activations