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

    Neuronpedia

    INDEX
    Explanations

    references to the "Old" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .cx
    -0.17
    alyze
    -0.15
    168
    -0.15
    alm
    -0.15
    391
    -0.15
    atrix
    -0.14
    789
    -0.14
    ote
    -0.14
    izer
    -0.14
    ushi
    -0.14
    POSITIVE LOGITS
    enburg
    0.29
    endor
    0.27
    ÅĻich
    0.26
    -fashioned
    0.26
     fashioned
    0.24
    ENDOR
    0.23
    /New
    0.21
    ham
    0.20
     Testament
    0.20
    /new
    0.20
    Act Density 0.029%

    No Known Activations