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

    Neuronpedia

    INDEX
    Explanations

    phrases related to outlining or detailing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uyar
    -0.14
     poor
    -0.14
    253
    -0.14
    presso
    -0.13
    echa
    -0.13
     TRACE
    -0.13
     disgr
    -0.13
    raki
    -0.13
     seedu
    -0.13
    èIJ½
    -0.13
    POSITIVE LOGITS
     how
    0.25
     briefly
    0.22
     why
    0.20
    how
    0.18
    å¦Ĥä½ķ
    0.18
     detail
    0.18
    æĢİä¹Ī
    0.17
     details
    0.17
     precisely
    0.17
     ways
    0.17
    Act Density 0.112%

    No Known Activations