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

    Neuronpedia

    INDEX
    Explanations

    words related to job positions and personnel changes

    oai_token-act-pair · gpt-3.5-turbo

    events or changes related to significant departures or resignations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     invent
    -0.75
     roam
    -0.74
     Ort
    -0.71
     capacities
    -0.70
     Practices
    -0.70
     specialize
    -0.66
    ngth
    -0.66
     excel
    -0.64
    essor
    -0.63
     Cosponsors
    -0.63
    POSITIVE LOGITS
     postponed
    1.25
     bitters
    1.23
     imminent
    1.22
     inevitable
    1.12
     instantaneous
    1.11
     irreversible
    1.08
     delayed
    1.06
     abrupt
    1.01
     unthinkable
    0.97
     swift
    0.96
    Act Density 0.356%

    No Known Activations