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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proximity or closeness

    oai_token-act-pair · gpt-3.5-turbo

    the word "close" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.84
    PLA
    -0.75
    ERG
    -0.69
    OGR
    -0.68
     behav
    -0.68
    ury
    -0.68
    Ĥª
    -0.66
    KC
    -0.65
    RF
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
    sighted
    0.89
     shore
    0.87
    shore
    0.77
     attain
    0.77
    amaru
    0.76
     achieving
    0.70
    ffee
    0.70
     reach
    0.69
     Confederation
    0.68
     1600
    0.68
    Act Density 0.048%

    No Known Activations