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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coff
    -0.16
    zes
    -0.15
    uhan
    -0.14
    ifen
    -0.14
    gia
    -0.14
    ts
    -0.14
    vyk
    -0.14
    anship
    -0.14
     íŀĺ
    -0.13
    VERTISE
    -0.13
    POSITIVE LOGITS
     Kurd
    0.15
    AccessException
    0.14
    bam
    0.14
    oppers
    0.14
    bble
    0.14
    ilst
    0.13
     Pond
    0.13
    aged
    0.13
    oppable
    0.13
    ehler
    0.13
    Act Density 0.346%

    No Known Activations