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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the symbol 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favorably
    -0.91
     favor
    -0.86
     favoring
    -0.84
     favored
    -0.84
    ©¶æ
    -0.84
     harbor
    -0.80
     caliber
    -0.77
    ĪĴ
    -0.73
     behaviors
    -0.73
     flavors
    -0.73
    POSITIVE LOGITS
    However
    1.40
    Speaking
    1.24
    But
    1.22
    Topics
    1.22
    Having
    1.19
    Meanwhile
    1.18
    Scotland
    1.17
    Writing
    1.16
    Scroll
    1.16
    Labour
    1.16
    Act Density 0.467%

    No Known Activations