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

    Neuronpedia

    INDEX
    Explanations

    phrases describing close competition or conflict between entities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships between subjects and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.78
    >[
    -0.76
    ãĤ¤ãĥĪ
    -0.68
    states
    -0.68
    States
    -0.66
    ãĤ©
    -0.64
    CLASSIFIED
    -0.64
    ILE
    -0.64
    SPONSORED
    -0.63
    IUM
    -0.63
    POSITIVE LOGITS
     toe
    1.19
     heels
    1.09
    toe
    1.05
     heel
    1.02
     foot
    0.99
     glove
    0.96
     toes
    0.94
     shoulder
    0.90
     mouth
    0.89
     tooth
    0.88
    Act Density 0.034%

    No Known Activations