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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional positions and actions related to leaving them

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being fired or resigning from a position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Registered
    -0.84
    eh
    -0.74
    olin
    -0.69
    rawdownloadcloneembedreportprint
    -0.68
    obi
    -0.68
     ideally
    -0.67
    Place
    -0.67
    bowl
    -0.66
    pac
    -0.66
    CO
    -0.65
    POSITIVE LOGITS
     disagreements
    1.09
     allegations
    0.96
     objections
    0.90
     outcry
    0.90
     misconduct
    0.88
     violations
    0.87
     complaints
    0.86
     accusations
    0.86
     disagreement
    0.85
     breaching
    0.85
    Act Density 0.259%

    No Known Activations