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

    Neuronpedia

    INDEX
    Explanations

    the word "those" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usz
    -0.14
    mpar
    -0.14
    iná
    -0.14
    æĬ½
    -0.14
    ped
    -0.14
    egen
    -0.13
    ashing
    -0.13
    alty
    -0.13
    pio
    -0.13
    pert
    -0.13
    POSITIVE LOGITS
    unky
    0.17
     Huck
    0.15
    immune
    0.15
    Ú©ÛĮÙĦ
    0.15
    dra
    0.14
    üme
    0.14
    nonnull
    0.14
    uba
    0.14
    deÅŁ
    0.14
     Tüm
    0.14
    Act Density 0.020%

    No Known Activations