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

    Neuronpedia

    INDEX
    Explanations

    the phrase "near future" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proximity in time or space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.69
    arians
    -0.67
    Ĥª
    -0.67
     Clubs
    -0.66
    gae
    -0.65
    hops
    -0.64
    ilus
    -0.64
     Females
    -0.64
    istry
    -0.64
    Tips
    -0.63
    POSITIVE LOGITS
    sighted
    1.21
    shore
    0.93
    entimes
    0.87
     misses
    0.85
     mint
    0.78
    ctic
    0.76
    zero
    0.74
     unanimous
    0.71
    utherford
    0.70
    -
    0.69
    Act Density 0.032%

    No Known Activations