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

    Neuronpedia

    INDEX
    Explanations

    language related to social inequalities and their impact on vulnerable populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSIP
    -0.19
     interrupt
    -0.17
     TIMEOUT
    -0.15
    Enlarge
    -0.15
     deadlock
    -0.15
    unce
    -0.15
    طاÙĨ
    -0.15
     INTERRU
    -0.14
     Assass
    -0.14
    eri
    -0.14
    POSITIVE LOGITS
     affected
    0.38
    affected
    0.33
    Affected
    0.31
     victim
    0.30
     victims
    0.29
     Victims
    0.26
     unaffected
    0.25
     targets
    0.25
     impacted
    0.25
     casualties
    0.25
    Act Density 0.012%

    No Known Activations