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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific job positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    references to employment and job-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oops
    -0.62
    ril
    -0.61
    Cause
    -0.59
    .''.
    -0.59
    ————————————————
    -0.59
    oshenko
    -0.57
    WF
    -0.57
    )).
    -0.57
    cause
    -0.56
    trigger
    -0.55
    POSITIVE LOGITS
    ipel
    0.68
    eous
    0.66
     analogy
    0.62
     nutshell
    0.62
    abad
    0.60
    lance
    0.59
     vantage
    0.57
    occupied
    0.56
     jargon
    0.55
     Awareness
    0.54
    Act Density 0.869%

    No Known Activations