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

    Neuronpedia

    INDEX
    Explanations

    phrases related to having knowledge or experience in a particular field

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the phrase "we have."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imo
    -0.81
    weed
    -0.74
    âĺħ
    -0.68
    oshi
    -0.68
    eem
    -0.67
    attery
    -0.64
    TG
    -0.61
    inducing
    -0.61
    drive
    -0.61
    ogo
    -0.60
    POSITIVE LOGITS
     ourselves
    1.22
     been
    1.02
     seen
    1.01
     heard
    0.92
     witnessed
    0.88
     gotten
    0.86
     talked
    0.85
     our
    0.85
     begun
    0.84
     learned
    0.80
    Act Density 0.139%

    No Known Activations