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

    Neuronpedia

    INDEX
    Explanations

    mentions of activities or objects related to ice

    oai_token-act-pair · gpt-3.5-turbo

    references to ice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anan
    -0.74
    enance
    -0.68
     QR
    -0.65
    nesday
    -0.63
    ENTION
    -0.63
    itory
    -0.62
     Greenwood
    -0.62
    edy
    -0.62
    ibly
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    POSITIVE LOGITS
    cream
    1.39
    breaker
    1.28
    breakers
    1.27
     cream
    1.25
    berg
    1.07
     skating
    1.06
     rink
    1.05
    pick
    1.03
     Cream
    1.00
    caps
    0.99
    Act Density 0.030%

    No Known Activations