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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with "That" and describe a specific action or situation

    oai_token-act-pair · gpt-3.5-turbo

    the word "That" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.73
    "],"
    -0.72
    hips
    -0.66
    thro
    -0.66
    leeve
    -0.62
    rior
    -0.61
    Haw
    -0.60
    ãĥĥãĤ¯
    -0.60
    YS
    -0.59
    emis
    -0.59
    POSITIVE LOGITS
     mattered
    0.91
    cher
    0.90
     culminated
    0.81
     pesky
    0.78
     fateful
    0.78
     includes
    0.77
     resulted
    0.75
     sounds
    0.73
     entails
    0.72
     same
    0.71
    Act Density 0.094%

    No Known Activations