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

    Neuronpedia

    INDEX
    Explanations

    references to various universities and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irt
    -0.16
    аÑĤа
    -0.15
    atha
    -0.15
    zza
    -0.15
    assa
    -0.14
    uy
    -0.14
    çķ¥
    -0.14
    akh
    -0.14
    еÑģа
    -0.14
    aux
    -0.13
    POSITIVE LOGITS
     Southern
    0.19
     Notre
    0.18
     Evans
    0.18
     Phoenix
    0.17
     Northern
    0.17
    redient
    0.17
     Bridge
    0.16
     phoenix
    0.16
     Santo
    0.16
     Pike
    0.16
    Act Density 0.012%

    No Known Activations