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

    Neuronpedia

    INDEX
    Explanations

    phrases related to learning or gaining knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to learning and acquiring knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.74
    lished
    -0.74
    cohol
    -0.73
    athi
    -0.66
    riott
    -0.65
    vertisement
    -0.64
    omo
    -0.63
    idia
    -0.63
    pload
    -0.62
    atu
    -0.61
    POSITIVE LOGITS
     lesson
    1.07
     firsthand
    1.02
     lessons
    0.91
     basics
    0.78
     anew
    0.78
     tricks
    0.75
     Lessons
    0.74
     skills
    0.74
     playbook
    0.72
    >(
    0.71
    Act Density 0.146%

    No Known Activations