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

    Neuronpedia

    INDEX
    Explanations

    numerical values indicating quantity

    oai_token-act-pair · gpt-3.5-turbo

    the special token indicating the end of a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IAS
    -0.84
    anything
    -0.80
    ESE
    -0.73
    nothing
    -0.71
    doesn
    -0.70
    claimer
    -0.68
    ola
    -0.68
    ifice
    -0.68
     thence
    -0.67
    fan
    -0.67
    POSITIVE LOGITS
     hundred
    1.81
     thousand
    1.60
     dozen
    1.59
     months
    1.12
     weeks
    1.08
     times
    1.06
    teenth
    1.05
     occasions
    1.04
     iterations
    1.01
     aspects
    1.01
    Act Density 0.048%

    No Known Activations