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

    Neuronpedia

    INDEX
    Explanations

    instances of demonstrative pronouns and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ale
    -0.15
    anson
    -0.14
    roll
    -0.14
    in
    -0.14
    ed
    -0.14
     behalf
    -0.13
    instr
    -0.13
    isher
    -0.13
     rollers
    -0.13
    ноÑģ
    -0.13
    POSITIVE LOGITS
    ãĥ£
    0.17
    UAGE
    0.16
    ullan
    0.15
    ehen
    0.14
    ahoma
    0.14
    MOOTH
    0.14
    .Delay
    0.14
    mtx
    0.14
    ynos
    0.14
    ylie
    0.14
    Act Density 0.206%

    No Known Activations