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

    Neuronpedia

    INDEX
    Explanations

    words related to work-related actions such as resignation and dismissal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resignations and dismissals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agog
    -0.87
    enegger
    -0.78
    atomic
    -0.75
    orically
    -0.74
    acebook
    -0.71
    igmatic
    -0.70
    iesta
    -0.69
    esthetic
    -0.67
    eva
    -0.67
    OPER
    -0.66
    POSITIVE LOGITS
    ishment
    0.89
    ãĥĭ
    0.82
    ary
    0.77
    ism
    0.75
     announcement
    0.74
     thereof
    0.72
     looms
    0.71
    isms
    0.70
     of
    0.70
     hurdle
    0.65
    Act Density 0.167%

    No Known Activations