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

    Neuronpedia

    INDEX
    Explanations

    terms related to neural imaging and interactions with neural networks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.68
     pleaſure
    -1.59
     ་་
    -1.58
     houſe
    -1.57
     purpoſe
    -1.55
     Houſe
    -1.52
     ſtate
    -1.52
    ſelf
    -1.49
     ſind
    -1.46
    ſelves
    -1.46
    POSITIVE LOGITS
     (
    1.32
     
    1.27
    ,
    1.21
     "
    1.17
    :
    1.07
    /
    1.05
     “
    1.03
     in
    1.01
    -
    1.01
     -
    1.00
    Act Density 10.950%

    No Known Activations