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

    Neuronpedia

    INDEX
    Explanations

    specific terms indicating locations or groups and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Handwerk
    -0.46
    -
    -0.46
     “
    -0.44
     Segen
    -0.41
     Priester
    -0.41
    ～
    -0.40
     Darum
    -0.40
     Dlatego
    -0.39
     mesin
    -0.39
     Feind
    -0.39
    POSITIVE LOGITS
     <>",
    0.81
    +#+
    0.77
     betweenstory
    0.75
    iſen
    0.69
    UserScript
    0.69
     <<<<<<<<<<<<<<
    0.66
    tagHelperRunner
    0.64
    0.63
     Савезне
    0.62
     gynhyrchwyd
    0.62
    Act Density 1.023%

    No Known Activations