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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of locations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wake
    -0.74
     elbow
    -0.73
    plet
    -0.72
    IRE
    -0.72
     volley
    -0.69
    itely
    -0.68
    zzle
    -0.68
    itory
    -0.68
     homework
    -0.67
     vape
    -0.67
    POSITIVE LOGITS
     Additionally
    1.32
     Therefore
    1.30
     Its
    1.29
     However
    1.26
     Furthermore
    1.26
     Located
    1.23
     Moreover
    1.23
     Also
    1.23
     Consequently
    1.22
     Interestingly
    1.18
    Act Density 0.711%

    No Known Activations