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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases that convey emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.25
     atleast
    -0.24
     actually
    -0.24
     only
    -0.23
     quite
    -0.22
     definitely
    -0.21
     certainly
    -0.21
     even
    -0.21
     least
    -0.20
    only
    -0.20
    POSITIVE LOGITS
     thôi
    0.23
     plain
    0.22
    æĻ®éĢļ
    0.22
     ordinary
    0.20
    ordinary
    0.19
    ifiable
    0.18
    ifi
    0.18
     simple
    0.18
    simple
    0.17
     nữa
    0.17
    Act Density 0.268%

    No Known Activations