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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the concept of reference or mentioning

    oai_token-act-pair · gpt-3.5-turbo

    references to the verb "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.69
     behav
    -0.67
    hops
    -0.66
    okia
    -0.66
    tun
    -0.65
    resy
    -0.64
    wine
    -0.64
    need
    -0.63
    thumbnails
    -0.62
     depended
    -0.62
    POSITIVE LOGITS
    asted
    0.88
     shore
    0.79
    asty
    0.77
    wards
    0.76
    icial
    0.73
    ggles
    0.72
    ffee
    0.70
    tnc
    0.69
     the
    0.69
     ours
    0.68
    Act Density 0.693%

    No Known Activations