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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "retired" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ån
    -0.16
    uteur
    -0.16
    stru
    -0.15
    heit
    -0.15
    atten
    -0.15
    heading
    -0.15
    erland
    -0.15
    oles
    -0.15
    erif
    -0.14
    ptions
    -0.14
    POSITIVE LOGITS
     ret
    0.22
    (ret
    0.22
    ired
    0.22
     retina
    0.21
     Ret
    0.21
    irement
    0.19
    tsy
    0.19
     RET
    0.18
    .Ret
    0.18
    inal
    0.17
    Act Density 0.015%

    No Known Activations