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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or assessments between different groups or categories

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to group demographics or social categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldemort
    -0.82
    chio
    -0.72
    aminer
    -0.71
    ossession
    -0.71
    icter
    -0.71
    ellation
    -0.70
    ickr
    -0.70
    emb
    -0.69
    ounter
    -0.67
    ivation
    -0.66
    POSITIVE LOGITS
     peers
    0.85
     whom
    0.84
     us
    0.81
     respondents
    0.77
     those
    0.77
     them
    0.76
    friends
    0.75
     fellow
    0.74
     voters
    0.73
     members
    0.71
    Act Density 0.028%

    No Known Activations