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

    Neuronpedia

    INDEX
    Explanations

    declarative statements involving knowledge or belief, often related to technology or information sharing

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating people's awareness or lack thereof regarding various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advertisement
    -0.73
    =/
    -0.66
     Sprite
    -0.65
     bearer
    -0.65
    ciation
    -0.64
     Humane
    -0.64
     Savannah
    -0.64
     Resurrection
    -0.63
     Deadly
    -0.63
     contestant
    -0.63
    POSITIVE LOGITS
     swear
    0.80
     mistakenly
    0.78
     misconceptions
    0.78
     unaware
    0.76
     wondering
    0.74
     perceive
    0.73
     poorer
    0.73
     underestimate
    0.72
     dissatisfied
    0.72
     experiencing
    0.72
    Act Density 0.333%

    No Known Activations