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

    Neuronpedia

    INDEX
    Explanations

    instances where someone makes contact or tries to communicate with others for various reasons

    oai_token-act-pair · gpt-3.5-turbo

    instances of reaching out to others for communication or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tsukuyomi
    -0.82
    cake
    -0.70
    ardo
    -0.65
     CARD
    -0.61
    antry
    -0.59
     Kats
    -0.59
     oxidation
    -0.58
    PET
    -0.58
     Syd
    -0.58
     Kru
    -0.58
    POSITIVE LOGITS
    stretched
    1.04
    doors
    0.88
    wards
    0.80
    posts
    0.74
    reach
    0.73
    door
    0.73
    reprene
    0.72
    worm
    0.70
    spr
    0.69
    reb
    0.69
    Act Density 0.021%

    No Known Activations