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

    Neuronpedia

    INDEX
    Explanations

    personal effort or attempted actions and their outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of effort and determination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.72
     Chow
    -0.68
    Bey
    -0.62
    Kings
    -0.62
    DragonMagazine
    -0.61
    minus
    -0.61
     Loch
    -0.60
     Splash
    -0.60
     Warn
    -0.59
     Roose
    -0.59
    POSITIVE LOGITS
     shaping
    0.80
    alion
    0.78
     endeav
    0.78
     erad
    0.76
     resolving
    0.74
    ãĤ¿
    0.72
     sorting
    0.72
     shielding
    0.71
     compiling
    0.70
    ework
    0.70
    Act Density 0.374%

    No Known Activations