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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings or official documents

    oai_token-act-pair · gpt-3.5-turbo

    indications of quantitative measures or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Floyd
    -0.84
     Chandler
    -0.80
     Arkansas
    -0.80
     Vanderbilt
    -0.80
     Boone
    -0.80
     homebrew
    -0.79
     Garrett
    -0.79
    boro
    -0.77
     ponies
    -0.77
     Baxter
    -0.76
    POSITIVE LOGITS
    Moreover
    1.25
    Therefore
    1.17
    Refer
    1.16
    Furthermore
    1.12
    Talking
    1.09
    However
    1.09
    Secondly
    1.09
    jriwal
    1.08
    Meanwhile
    1.08
    Pakistan
    1.05
    Act Density 0.477%

    No Known Activations