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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong recommendations or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chant
    -0.15
    afone
    -0.15
    angen
    -0.14
    wart
    -0.14
    ̣
    -0.14
    imde
    -0.13
    uble
    -0.13
    itra
    -0.13
    .AppendFormat
    -0.13
     retros
    -0.13
    POSITIVE LOGITS
     highly
    0.46
     Highly
    0.43
     recommend
    0.31
     HIGH
    0.30
     recom
    0.30
     strongly
    0.29
     recommendation
    0.27
     Recommend
    0.27
    æݨèįIJ
    0.27
     recommends
    0.26
    Act Density 0.046%

    No Known Activations