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

    Neuronpedia

    INDEX
    Explanations

    phrases related to undermining or destroying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political actions or implications that suggest harm or damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogg
    -0.70
    eller
    -0.70
     varies
    -0.69
     differs
    -0.69
     Unsure
    -0.68
     compares
    -0.65
    display
    -0.63
    deck
    -0.63
    osite
    -0.62
    zilla
    -0.62
    POSITIVE LOGITS
     credibility
    1.33
     livelihood
    1.10
     cherished
    1.08
     integrity
    1.07
     dignity
    1.05
     legitimacy
    1.03
     semblance
    1.01
     freedoms
    1.00
     morale
    0.97
     foundations
    0.97
    Act Density 0.527%

    No Known Activations