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

    Neuronpedia

    INDEX
    Explanations

    words related to socio-economic issues and policies

    oai_token-act-pair · gpt-3.5-turbo

    topics related to socio-economic challenges and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.66
    ç«
    -0.65
    代
    -0.63
     TBD
    -0.61
    sama
    -0.58
    Scope
    -0.58
    alion
    -0.56
     transpired
    -0.53
    timer
    -0.52
    ãĥ´ãĤ¡
    -0.52
    POSITIVE LOGITS
     themselves
    0.93
     their
    0.84
     careers
    0.77
    their
    0.75
     healthier
    0.75
     THEIR
    0.74
     lifestyles
    0.74
    utterstock
    0.71
    selves
    0.70
     incomes
    0.69
    Act Density 1.025%

    No Known Activations