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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or transitions indicating a statement or explanation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate certainty or express opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obal
    -0.88
     Cheong
    -0.71
    ritic
    -0.69
    ourses
    -0.68
    hammad
    -0.67
    oided
    -0.66
    alg
    -0.65
    uga
    -0.65
     Lumpur
    -0.64
    emouth
    -0.63
    POSITIVE LOGITS
    ties
    0.65
    erous
    0.64
     caveats
    0.63
    WHERE
    0.60
    !--
    0.60
    ,.
    0.59
     understatement
    0.59
    -----------
    0.58
    bear
    0.58
    advertising
    0.57
    Act Density 0.065%

    No Known Activations