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

    Neuronpedia

    INDEX
    Explanations

    specific terms indicating human or alien beings in fictional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olon
    -0.17
    ogn
    -0.16
    ATUS
    -0.15
    amientos
    -0.15
    iasm
    -0.15
    ANEL
    -0.15
    enta
    -0.15
    aceut
    -0.14
    bote
    -0.14
    .renderer
    -0.14
    POSITIVE LOGITS
    ëłĩ
    0.15
    aggio
    0.14
    igor
    0.14
     Sür
    0.14
     Gate
    0.14
    PLICATION
    0.14
    IFY
    0.14
    imeo
    0.14
    unar
    0.14
    igaret
    0.13
    Act Density 0.028%

    No Known Activations