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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    dates and numbers in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pom
    -0.81
    pex
    -0.81
     Porter
    -0.77
     Piper
    -0.77
     DP
    -0.77
     Pam
    -0.77
    zzo
    -0.75
    aminer
    -0.71
    rup
    -0.71
     Mex
    -0.70
    POSITIVE LOGITS
    17
    1.58
    16
    1.48
     17
    1.45
    18
    1.39
     16
    1.30
     18
    1.19
    15
    1.13
     eighteenth
    1.11
    169
    1.07
    19
    1.03
    Act Density 0.229%

    No Known Activations