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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.79
     ogre
    -0.78
     semblance
    -0.74
     transact
    -0.73
     enclosure
    -0.72
     grunt
    -0.70
     cradle
    -0.70
     loyalty
    -0.69
     powering
    -0.68
     interference
    -0.68
    POSITIVE LOGITS
     Regarding
    0.93
     Whereas
    0.90
     Firstly
    0.90
    psc
    0.90
     Their
    0.90
     However
    0.89
     Though
    0.88
     Flavoring
    0.88
    dk
    0.88
     Asked
    0.87
    Act Density 0.076%

    No Known Activations