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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight recognition or reputation for accomplishments or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anon
    -0.15
    aldo
    -0.15
    inel
    -0.14
    inder
    -0.14
    imen
    -0.14
     Waters
    -0.14
    .ReadAll
    -0.14
    yla
    -0.14
    porn
    -0.13
    ect
    -0.13
    POSITIVE LOGITS
    istik
    0.15
    ¯ÃĤ
    0.15
     bare
    0.15
    PLIC
    0.15
     CreateMap
    0.14
     its
    0.14
    bare
    0.14
    LOPT
    0.14
    672
    0.14
    .handlers
    0.14
    Act Density 0.133%

    No Known Activations