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

    Neuronpedia

    INDEX
    Explanations

    locations and events related to various cities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "))
    -0.82
    Isn
    -0.66
    ¶
    -0.65
    obyl
    -0.65
    acus
    -0.64
    lihood
    -0.63
     piss
    -0.62
    Recently
    -0.60
     terrified
    -0.58
    often
    -0.57
    POSITIVE LOGITS
     until
    1.16
     unless
    1.14
     tomorrow
    1.00
     respectively
    0.93
     except
    0.91
     beginning
    0.91
     whichever
    0.88
     regardless
    0.88
     pending
    0.87
     excluding
    0.85
    Act Density 0.580%

    No Known Activations