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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction and aftermath

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to destruction and absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rike
    -0.74
    rano
    -0.68
    racuse
    -0.67
    izoph
    -0.65
    ribed
    -0.65
    rosse
    -0.64
    Detect
    -0.63
    olf
    -0.62
    riz
    -0.61
    Choice
    -0.61
    POSITIVE LOGITS
     remnants
    0.81
    warm
    0.80
     cushion
    0.75
    belt
    0.73
     remnant
    0.71
     Cinderella
    0.70
     Recon
    0.70
    çĶŁ
    0.68
     awaiting
    0.68
     cush
    0.68
    Act Density 0.144%

    No Known Activations