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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     …
    -0.88
     …)
    -0.81
     ….
    -0.81
    ՚
    -0.80
     JpaRepository
    -0.78
    …~
    -0.77
     autorytatywna
    -0.75
     ¦
    -0.74
     …”
    -0.74
     …………
    -0.74
    POSITIVE LOGITS
    --
    0.72
    ...
    0.71
    ​
    0.69
     --
    0.64
     postIndex
    0.58
    '''
    0.58
    ....
    0.57
    ---
    0.56
    </h6>
    0.56
    '--
    0.55
    Act Density 0.566%

    No Known Activations