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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or strong recommendation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realmente
    -0.26
     actually
    -0.24
    actually
    -0.23
     basically
    -0.22
     Actually
    -0.21
    Actually
    -0.21
     wirklich
    -0.21
    ç«Ł
    -0.20
     aslında
    -0.20
    åħ¶å®ŀ
    -0.20
    POSITIVE LOGITS
     wouldn
    0.18
     nowhere
    0.17
    ;y
    0.16
     none
    0.16
     plenty
    0.15
    684
    0.15
    ãģªãģĮãĤī
    0.15
     alguna
    0.15
    AMIL
    0.15
     worth
    0.14
    Act Density 0.194%

    No Known Activations