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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dime
    -0.99
     defe
    -0.81
     paycheck
    -0.78
     unloaded
    -0.78
     uncom
    -0.75
     glim
    -0.74
     royalty
    -0.72
     honoring
    -0.71
     hurricane
    -0.71
     millisec
    -0.71
    POSITIVE LOGITS
     Hence
    1.21
     Moreover
    1.19
     Whilst
    1.16
     Afterwards
    1.10
     However
    1.10
     Furthermore
    1.09
     Alternatively
    1.08
     Rohing
    1.07
     Malays
    1.06
     Kerala
    1.06
    Act Density 0.451%

    No Known Activations