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

    Neuronpedia

    INDEX
    Explanations

    specific names or titles related to media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wig
    -0.15
     Griffin
    -0.15
     Dias
    -0.14
    erring
    -0.14
    gue
    -0.14
     diversified
    -0.13
    ihan
    -0.13
     Christ
    -0.13
     rec
    -0.13
    antes
    -0.13
    POSITIVE LOGITS
    ása
    0.26
    ja
    0.21
    isa
    0.21
    tere
    0.21
    nete
    0.21
    adata
    0.21
    je
    0.20
    uma
    0.20
    ISA
    0.20
    atak
    0.20
    Act Density 0.000%

    No Known Activations