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

    Neuronpedia

    INDEX
    Explanations

    references to literary works or notable texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loc
    -0.14
    rowsing
    -0.14
     Nec
    -0.14
    ÏĦι
    -0.14
     Nested
    -0.14
    agal
    -0.13
     userdata
    -0.13
    ertiary
    -0.13
    quip
    -0.13
    assa
    -0.13
    POSITIVE LOGITS
     Jewish
    0.23
     hiding
    0.21
     Zionist
    0.20
     Resistance
    0.20
     Jews
    0.19
     Blitz
    0.19
     hide
    0.19
     Hide
    0.18
     Kinder
    0.18
     Anne
    0.18
    Act Density 0.010%

    No Known Activations