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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    the word "among" in contexts relating to groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chio
    -0.76
    oldemort
    -0.70
    icter
    -0.68
    ickr
    -0.68
     prol
    -0.67
    di
    -0.66
    onna
    -0.66
    iris
    -0.66
    emb
    -0.65
    aminer
    -0.64
    POSITIVE LOGITS
     peers
    0.87
     us
    0.82
     those
    0.80
     onlook
    0.78
    warts
    0.77
     them
    0.76
     whom
    0.76
     respondents
    0.75
     participants
    0.73
     passers
    0.71
    Act Density 0.036%

    No Known Activations