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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific organizational names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongs
    -0.15
    xon
    -0.15
    yg
    -0.15
     ple
    -0.15
    lok
    -0.14
    uts
    -0.14
    ito
    -0.14
    ÑĢаÑĩ
    -0.14
    nak
    -0.14
    igg
    -0.13
    POSITIVE LOGITS
     incom
    0.17
    undef
    0.17
    ¿
    0.17
    odore
    0.17
     folks
    0.16
    äºŃ
    0.16
     nackte
    0.16
    ehir
    0.16
    iosper
    0.16
     firm
    0.15
    Act Density 0.140%

    No Known Activations