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

    Neuronpedia

    INDEX
    Explanations

    instances where the concept of 'coming close' is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proximity or closeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ai
    -0.69
     Lieberman
    -0.66
    uria
    -0.66
     Dwarf
    -0.63
    Austral
    -0.63
    ople
    -0.62
    âĵĺ
    -0.61
    insert
    -0.61
    oret
    -0.59
    database
    -0.58
    POSITIVE LOGITS
     minded
    0.79
    sighted
    0.76
    terness
    0.76
    zynski
    0.72
    heed
    0.70
     enough
    0.69
    bley
    0.68
    animous
    0.68
    etr
    0.67
    lier
    0.67
    Act Density 0.027%

    No Known Activations