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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unity and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "together."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interest
    -0.63
    ysis
    -0.61
    null
    -0.60
     Gear
    -0.58
    mon
    -0.58
    ck
    -0.58
    1000
    -0.58
    ream
    -0.58
     Zam
    -0.58
    dark
    -0.57
    POSITIVE LOGITS
    é¾įå¥ij士
    0.89
    halla
    0.83
     together
    0.82
     arrang
    0.82
     behavi
    0.78
    ÃįÃį
    0.77
    åij
    0.76
     proport
    0.75
    eatures
    0.73
    Community
    0.73
    Act Density 0.020%

    No Known Activations