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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names, likely people or places

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or punctuation that may signify an important aspect of the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stre
    -0.75
    TERN
    -0.75
     Tenth
    -0.72
     WiFi
    -0.71
    PDATE
    -0.69
     Gravity
    -0.69
     Ply
    -0.67
     Polk
    -0.67
     Pigs
    -0.66
     Stellar
    -0.66
    POSITIVE LOGITS
    af
    1.33
    ak
    1.32
    ach
    1.26
    atche
    1.23
    á
    1.22
    ac
    1.21
    atar
    1.20
    av
    1.20
    awar
    1.17
    aj
    1.16
    Act Density 0.216%

    No Known Activations