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

    Neuronpedia

    INDEX
    Explanations

    incidents involving crime and legal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
    存于互联网档案馆
    -0.62
    wpi
    -0.59
    tagHelperRunner
    -0.58
    GEBURTSDATUM
    -0.58
     <<<<<<<<<<<<<<
    -0.56
    ApplicationTests
    -0.53
    migrationBuilder
    -0.52
    nyttet
    -0.52
     незавершена
    -0.51
    POSITIVE LOGITS
     suspect
    0.82
     woman
    0.75
     suspects
    0.63
     man
    0.63
     stabbing
    0.61
     victim
    0.61
    SPATH
    0.61
     sospe
    0.60
     mother
    0.57
     roommate
    0.56
    Act Density 0.275%

    No Known Activations