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

    Neuronpedia

    INDEX
    Explanations

    instances of communication and inquiry about thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouch
    -0.16
    andon
    -0.15
    strand
    -0.15
    adox
    -0.15
    .Focused
    -0.15
    ussen
    -0.14
    reau
    -0.14
    wig
    -0.14
     Rica
    -0.14
    biên
    -0.14
    POSITIVE LOGITS
     involving
    0.17
    пп
    0.15
     Mess
    0.15
    ttp
    0.15
     Shelter
    0.14
    à¥Ĥत
    0.14
     shelter
    0.14
    ÎŃÏģγ
    0.13
    Ľ°
    0.13
    æĭĶ
    0.13
    Act Density 0.260%

    No Known Activations