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

    Neuronpedia

    INDEX
    Explanations

    words related to having belief or trust in something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.92
    pmwiki
    -0.90
    Vert
    -0.84
    çĦ
    -0.72
    kay
    -0.70
    Mars
    -0.70
    artifacts
    -0.68
    bard
    -0.68
     UCHIJ
    -0.67
    area
    -0.66
    POSITIVE LOGITS
    ially
    1.07
    worthiness
    0.91
    iated
    0.88
    urances
    0.82
    ieth
    0.78
     assurance
    0.78
     confident
    0.76
    ipes
    0.74
     confidence
    0.74
    ively
    0.74
    Act Density 0.024%

    No Known Activations