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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people in large numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people, particularly in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cer
    -0.79
    tein
    -0.78
    ces
    -0.76
    Acknowled
    -0.74
    Es
    -0.70
    cknowled
    -0.67
    ten
    -0.66
    vious
    -0.66
    Britain
    -0.64
    ce
    -0.63
    POSITIVE LOGITS
     masses
    1.26
     tremend
    0.83
    olutions
    0.77
    urch
    0.76
    roots
    0.73
    astered
    0.73
    ourcing
    0.72
    uling
    0.71
    ngth
    0.71
    urion
    0.71
    Act Density 0.007%

    No Known Activations