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

    Neuronpedia

    INDEX
    Explanations

    statements about quantitative increases or rises in numbers

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "to" followed by various numerals or phrases indicating rising values or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riger
    -0.67
     outgoing
    -0.65
     transmitted
    -0.65
    sbm
    -0.63
     behav
    -0.63
    VPN
    -0.62
    tun
    -0.61
     ling
    -0.61
     innate
    -0.61
     packets
    -0.60
    POSITIVE LOGITS
    ggles
    1.02
    othy
    0.87
    éĹĺ
    0.85
     shorten
    0.82
     encompass
    0.80
     stabilize
    0.80
     defend
    0.79
    pless
    0.79
     eliminate
    0.79
     accommodate
    0.78
    Act Density 0.165%

    No Known Activations