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

    Neuronpedia

    INDEX
    Explanations

    financial values expressed in euros

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to economic figures or financial statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.64
     Klu
    -0.63
     Defenders
    -0.63
     Mesa
    -0.62
     ii
    -0.60
     Uncle
    -0.60
    etting
    -0.59
     Rouge
    -0.59
     Theodore
    -0.59
     Dill
    -0.58
    POSITIVE LOGITS
    something
    1.44
    percent
    1.40
    minute
    1.39
    plus
    1.37
    odd
    1.36
    year
    1.31
    degree
    1.26
    hour
    1.24
    second
    1.21
    yard
    1.17
    Act Density 0.060%

    No Known Activations