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

    Neuronpedia

    INDEX
    Explanations

    the word "in" used frequently to indicate location or context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fact
    -0.19
     fact
    -0.19
     facto
    -0.16
    added
    -0.16
     addition
    -0.16
     added
    -0.16
    turn
    -0.16
    Fact
    -0.15
    -turn
    -0.15
     also
    -0.15
    POSITIVE LOGITS
     Episode
    0.22
     episode
    0.21
     his
    0.20
    Episode
    0.17
    his
    0.15
    ä»ĸçļĦ
    0.15
     today
    0.15
    episode
    0.15
     tod
    0.15
    184
    0.14
    Act Density 0.074%

    No Known Activations