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

    Neuronpedia

    INDEX
    Explanations

    keywords related to current events or subjects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    jah
    -0.81
    ppings
    -0.78
    once
    -0.75
    ËĪ
    -0.73
    alty
    -0.72
    apist
    -0.71
    phy
    -0.69
    eneg
    -0.69
    DERR
    -0.67
    phia
    -0.67
    POSITIVE LOGITS
     whereabouts
    1.06
     occupant
    0.99
     incarnation
    0.92
     trends
    0.91
     affairs
    0.87
     iteration
    0.80
     vacancies
    0.79
    ties
    0.76
     crop
    0.76
     predicament
    0.72
    Act Density 0.041%

    No Known Activations