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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing a specific subject and exploring the consequences or implications of that subject

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "],"
    -0.78
    rior
    -0.70
    hips
    -0.66
    emis
    -0.62
    016
    -0.62
     Directions
    -0.62
    ãĥĺ
    -0.62
    waters
    -0.61
    kamp
    -0.60
     Pass
    -0.58
    POSITIVE LOGITS
     pesky
    0.99
     fateful
    0.91
     mattered
    0.80
     evening
    0.75
     culminated
    0.74
    cher
    0.73
     kind
    0.73
    eatures
    0.73
     afternoon
    0.71
    ÃĥÃĤ
    0.70
    Act Density 0.604%

    No Known Activations