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

    Neuronpedia

    INDEX
    Explanations

    terms related to energy, research, and education programs

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to energy, prevention, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jad
    -0.74
     Cheong
    -0.72
    anon
    -0.71
     Dull
    -0.70
    glas
    -0.65
    lves
    -0.65
     sweat
    -0.64
    atari
    -0.62
    gall
    -0.62
     Doomsday
    -0.62
    POSITIVE LOGITS
     sake
    1.61
     purposes
    1.58
     reasons
    1.12
    ummies
    1.02
     purpose
    0.88
     eternity
    0.85
     reason
    0.72
     induction
    0.69
     upcoming
    0.68
     Reasons
    0.68
    Act Density 1.280%

    No Known Activations