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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iirc
    -0.63
    Согласно
    -0.59
    WithIOException
    -0.57
     IIRC
    -0.55
    Interestingly
    -0.55
    whereas
    -0.54
     According
    -0.53
    According
    -0.53
     Similar
    -0.51
    queryInterface
    -0.51
    POSITIVE LOGITS
     thank
    1.05
     especially
    0.93
     THANK
    0.92
     🙏
    0.86
    especially
    0.84
    THANK
    0.82
     bedankt
    0.79
    thank
    0.79
     remercier
    0.79
     especialmente
    0.78
    Act Density 0.207%

    No Known Activations