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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding or comprehending something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hens
    -0.78
    orah
    -0.75
    oran
    -0.73
    isers
    -0.72
    yn
    -0.68
    obb
    -0.68
    rack
    -0.67
    aughtered
    -0.67
    ostics
    -0.67
    ostic
    -0.66
    POSITIVE LOGITS
     there
    0.88
     someday
    0.83
     they
    0.82
     pesky
    0.77
     although
    0.77
     THERE
    0.75
     whereas
    0.74
     fateful
    0.73
     THEY
    0.72
     despite
    0.67
    Act Density 0.203%

    No Known Activations