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

    Neuronpedia

    INDEX
    Explanations

    phrases related to infrastructure issues

    oai_token-act-pair · gpt-3.5-turbo

    references to public health issues and facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eras
    -0.86
     Founding
    -0.74
     greatness
    -0.74
     immortal
    -0.71
     immortality
    -0.71
     seminal
    -0.69
     embrace
    -0.68
     orb
    -0.68
     evolved
    -0.68
     distinguished
    -0.67
    POSITIVE LOGITS
     Worse
    1.04
    Residents
    0.87
     worsening
    0.87
     landlords
    0.83
     UNHCR
    0.83
     Residents
    0.82
     desperation
    0.82
     Meanwhile
    0.81
     eviction
    0.80
     residents
    0.79
    Act Density 1.047%

    No Known Activations