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

    Neuronpedia

    INDEX
    Explanations

    words related to different aspects of work and careers

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of work and their implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.76
    YC
    -0.72
    quished
    -0.68
    ivan
    -0.68
    obook
    -0.66
    sbm
    -0.66
    :[
    -0.63
    ottest
    -0.62
     nominated
    -0.61
    çīĪ
    -0.60
    POSITIVE LOGITS
     causation
    0.85
     etc
    0.70
    grain
    0.67
    science
    0.67
     digestion
    0.66
     nuance
    0.66
     manipulation
    0.66
     obscurity
    0.64
     albeit
    0.64
     understatement
    0.63
    Act Density 0.643%

    No Known Activations