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

    Neuronpedia

    INDEX
    Explanations

    phrases related to work and professions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to work and employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dot
    -0.75
    reme
    -0.74
    threat
    -0.73
    vati
    -0.69
    onen
    -0.69
    etus
    -0.64
     stormed
    -0.64
    pour
    -0.64
    oxide
    -0.63
     mosqu
    -0.62
    POSITIVE LOGITS
     diligence
    0.75
     apprentices
    0.72
     productivity
    0.71
     Engels
    0.69
    umen
    0.69
     completion
    0.64
    ijk
    0.64
     manuals
    0.63
     miracles
    0.63
     briefs
    0.63
    Act Density 0.247%

    No Known Activations