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

    Neuronpedia

    INDEX
    Explanations

    references to specific news articles and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yne
    -0.16
    zig
    -0.16
     ÙĪا
    -0.15
    sis
    -0.14
    122
    -0.14
    lesi
    -0.14
    ct
    -0.14
    yer
    -0.14
    алÑİ
    -0.14
    lers
    -0.13
    POSITIVE LOGITS
    undef
    0.19
     Hill
    0.18
    Wrap
    0.17
     Wrap
    0.17
     Washington
    0.17
    epoch
    0.17
     Christian
    0.17
     Hollywood
    0.16
     Wall
    0.16
    Atlantic
    0.16
    Act Density 0.039%

    No Known Activations