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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe something as unique or distinctive

    oai_token-act-pair · gpt-3.5-turbo

    features or aspects that distinguish something from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abus
    -0.62
     briefed
    -0.62
     memos
    -0.62
    artment
    -0.60
     consulted
    -0.60
     exchanged
    -0.60
     Contract
    -0.58
     Lack
    -0.58
     volunteered
    -0.57
    administ
    -0.56
    POSITIVE LOGITS
     leaps
    0.89
     acclaim
    0.85
     impressive
    0.85
     debut
    0.77
     acclaimed
    0.76
     renown
    0.75
     exciting
    0.75
     tremend
    0.75
     impress
    0.74
     contenders
    0.74
    Act Density 1.026%

    No Known Activations