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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spending time

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to spending time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elled
    -0.74
    ensen
    -0.68
    elin
    -0.66
    haps
    -0.64
    assis
    -0.64
    edom
    -0.64
    ulent
    -0.63
    artisan
    -0.62
    ottage
    -0.62
    het
    -0.62
    POSITIVE LOGITS
     outdoors
    0.91
     discussing
    0.82
     worrying
    0.80
     exploring
    0.80
     chatting
    0.78
    frame
    0.75
     studying
    0.74
     traveling
    0.73
    frames
    0.72
     interacting
    0.72
    Act Density 0.040%

    No Known Activations