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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     congratulations
    -0.17
     Congratulations
    -0.16
     congratulate
    -0.15
     congrat
    -0.15
    follower
    -0.14
    alian
    -0.14
    andin
    -0.14
     Cong
    -0.14
    Congratulations
    -0.14
    reasonable
    -0.14
    POSITIVE LOGITS
     appreciated
    0.65
     appreciate
    0.59
     Apprec
    0.57
     appreciation
    0.52
     apprec
    0.49
     greatly
    0.38
     much
    0.29
    preci
    0.26
     Much
    0.26
    App
    0.26
    Act Density 0.057%

    No Known Activations