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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals working or collaborating on various projects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "worked."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iba
    -0.65
     initiation
    -0.64
     invasion
    -0.57
     invading
    -0.57
    mount
    -0.57
     indict
    -0.56
    rising
    -0.55
    ogens
    -0.54
     Registrar
    -0.54
     Deity
    -0.54
    POSITIVE LOGITS
     worked
    3.39
    worked
    1.99
     WORK
    1.82
     works
    1.70
     collaborated
    1.69
    Work
    1.63
     Work
    1.63
     work
    1.62
    work
    1.54
    Working
    1.52
    Act Density 0.018%

    No Known Activations