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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction or negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dest" or its variations, indicating a focus on destinations or related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    manship
    -0.78
    interstitial
    -0.73
    swer
    -0.73
    Reviewer
    -0.70
    culosis
    -0.70
    enegger
    -0.67
    SPONSORED
    -0.67
    esome
    -0.66
    GGGG
    -0.65
    ocene
    -0.65
    POSITIVE LOGITS
    roying
    1.26
    ruct
    1.25
    itute
    1.11
    ined
    1.04
    ination
    1.03
    inations
    1.03
    ruction
    1.00
    ãĥ´
    0.99
    iny
    0.93
    itution
    0.90
    Act Density 0.006%

    No Known Activations