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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.70
    robat
    -0.66
    ãĥīãĥ©
    -0.65
     extraord
    -0.64
    çīĪ
    -0.62
    ominated
    -0.61
    aimon
    -0.61
    atorium
    -0.59
    asma
    -0.59
    çļ
    -0.59
    POSITIVE LOGITS
     noting
    1.48
     adding
    1.44
     citing
    1.33
     stressing
    1.21
     pointing
    1.16
     saying
    1.12
     echoing
    1.09
     describing
    1.06
     referring
    1.06
     implying
    1.03
    Act Density 0.273%

    No Known Activations