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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical motion or movement in an upward direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emanuel
    -0.67
    Maker
    -0.66
     Administrator
    -0.61
    atically
    -0.60
    士
    -0.59
    pers
    -0.59
     firsthand
    -0.59
    ________________________
    -0.58
     Currency
    -0.58
    roid
    -0.57
    POSITIVE LOGITS
    stairs
    1.11
    rights
    1.10
    river
    0.98
    raised
    0.97
    draft
    0.93
    stage
    0.91
     stairs
    0.89
    dates
    0.89
    grades
    0.89
    ornia
    0.87
    Act Density 0.061%

    No Known Activations