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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" indicating emphasis or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    core
    -0.16
    ниÑĨе
    -0.16
    prd
    -0.16
    kaar
    -0.15
    едÑĮ
    -0.15
    tal
    -0.15
    panies
    -0.15
    ẻ
    -0.14
    lator
    -0.14
    dale
    -0.14
    POSITIVE LOGITS
    -called
    0.33
     forth
    0.22
    oner
    0.21
    aken
    0.19
     far
    0.19
    ething
    0.19
    ìį¨
    0.19
    forth
    0.19
    far
    0.19
    hn
    0.19
    Act Density 0.087%

    No Known Activations