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

    Neuronpedia

    INDEX
    Explanations

    words related to gaining advantage or progress

    oai_token-act-pair · gpt-3.5-turbo

    terms related to influence, control, or competition within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     particulars
    -0.64
     Tsukuyomi
    -0.62
    OTOS
    -0.61
    urst
    -0.60
     ACTIONS
    -0.59
    ãĥŁ
    -0.58
     coincidence
    -0.57
     batches
    -0.55
     Bucket
    -0.55
    ãĤ½
    -0.54
    POSITIVE LOGITS
     atop
    1.10
     among
    1.09
    hare
    1.05
     amongst
    1.03
     amidst
    0.89
     internationally
    0.88
     advantage
    0.85
     globally
    0.84
     amid
    0.83
     nationally
    0.83
    Act Density 0.185%

    No Known Activations