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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical closeness or tightness

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of constrained or limited situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.81
    代
    -0.74
    ablishment
    -0.72
     Twain
    -0.71
    ividual
    -0.70
    ista
    -0.69
    illery
    -0.68
    icative
    -0.68
     Courage
    -0.67
    ;;;;;;;;;;;;
    -0.67
    POSITIVE LOGITS
    ness
    1.08
    nesses
    1.03
    lining
    0.85
     tight
    0.83
     squeeze
    0.80
     fitting
    0.79
    heed
    0.79
    est
    0.78
    tail
    0.76
    weed
    0.76
    Act Density 0.017%

    No Known Activations