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

    Neuronpedia

    INDEX
    Explanations

    references to political agendas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    pite
    -0.69
    yste
    -0.68
    yaar
    -0.68
     Neto
    -0.65
     Isolation
    -0.61
     Boyle
    -0.60
    doms
    -0.60
    ťa
    -0.59
    Portály
    -0.59
    TabStop
    -0.59
    POSITIVE LOGITS
     Agenda
    1.81
     agenda
    1.76
    agenda
    1.69
     agendas
    1.65
    Agenda
    1.62
     AGENDA
    1.41
    AGENDA
    1.29
    cheiben
    0.86
     schedule
    0.84
     sched
    0.84
    Act Density 0.003%

    No Known Activations