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

    Neuronpedia

    INDEX
    Explanations

    phrases containing a transition from a past occupation or status to a current one

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a current state or position, particularly in relation to someone's past role or profession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acci
    -0.80
    rous
    -0.78
    reth
    -0.76
    pled
    -0.76
    ambo
    -0.74
    oned
    -0.73
     precon
    -0.70
     predis
    -0.70
    oglobin
    -0.69
    onomy
    -0.69
    POSITIVE LOGITS
    adays
    1.07
     defunct
    1.07
     retired
    1.03
     deceased
    0.93
     unemployed
    0.90
     unemploy
    0.87
     suing
    0.86
     residing
    0.85
     retire
    0.85
     renamed
    0.83
    Act Density 0.102%

    No Known Activations