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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement and community safety issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APS
    -0.16
    udge
    -0.16
    imuth
    -0.16
    ále
    -0.15
    Ý
    -0.14
     Hav
    -0.14
    uerdo
    -0.14
    ç²
    -0.14
    .sg
    -0.14
     Federal
    -0.14
    POSITIVE LOGITS
     Liberia
    0.35
     Liber
    0.32
    MON
    0.21
    LIB
    0.21
     Ebola
    0.20
     LIB
    0.20
     Nim
    0.20
    mon
    0.19
     Mon
    0.18
    Mon
    0.16
    Act Density 0.017%

    No Known Activations