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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences of underscores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.69
    ↵
    -0.63
    .
    -0.63
     
    -0.54
    <eos>
    -0.52
    ↵↵
    -0.50
    </b>
    -0.50
     (
    -0.50
    …
    -0.50
     "
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    1.44
     CreateTagHelper
    1.43
     myſelf
    1.34
     itſelf
    1.31
     pleaſure
    1.25
    RetentionPolicy
    1.24
     houſe
    1.20
    +#+
    1.20
     Efq
    1.20
     iſt
    1.19
    Act Density 0.380%

    No Known Activations