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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obeying instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "to" indicating direction or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rief
    -0.74
    rieve
    -0.70
     appealed
    -0.69
     mailed
    -0.68
    aukee
    -0.67
    ruce
    -0.67
    iba
    -0.66
    quartered
    -0.66
    ulence
    -0.65
    rieved
    -0.65
    POSITIVE LOGITS
     directions
    0.74
     tradition
    0.72
    Ô
    0.70
     Tradition
    0.70
     scripture
    0.67
    Lenin
    0.66
     varying
    0.65
     Wikipedia
    0.63
     standards
    0.63
     DSM
    0.62
    Act Density 0.071%

    No Known Activations