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

    Neuronpedia

    INDEX
    Explanations

    references to hiring or employing individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to hiring and employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.79
    xual
    -0.67
     spills
    -0.67
    myra
    -0.64
     accidents
    -0.63
    ipation
    -0.63
    oxicity
    -0.63
    resy
    -0.62
    士
    -0.61
     amput
    -0.60
    POSITIVE LOGITS
     secretaries
    0.80
     mercenaries
    0.80
     Cosponsors
    0.79
     assistants
    0.76
     helpers
    0.74
     mentor
    0.74
     Volunteers
    0.72
     masse
    0.72
     consultants
    0.70
     replacements
    0.70
    Act Density 0.270%

    No Known Activations