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

    Neuronpedia

    INDEX
    Explanations

    events or occasions where hosting by an entity is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hosted" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neg
    -0.71
    uyomi
    -0.70
    yth
    -0.68
    edia
    -0.66
    wd
    -0.66
    ogue
    -0.66
    onne
    -0.65
    imb
    -0.64
    ection
    -0.63
    vious
    -0.63
    POSITIVE LOGITS
     hosting
    0.90
     guests
    0.82
     host
    0.82
     hosted
    0.79
    Host
    0.77
    ilities
    0.73
    lift
    0.71
     hosts
    0.70
    ility
    0.68
     RTX
    0.68
    Act Density 0.019%

    No Known Activations