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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zelfde
    -0.42
    ↵↵
    -0.40
     lisäksi
    -0.37
     toepassing
    -0.36
     preparado
    -0.35
     mêmes
    -0.35
     sellado
    -0.33
     możli
    -0.33
     aikana
    -0.32
     trabajado
    -0.32
    POSITIVE LOGITS
    <unused43>
    0.77
    0.77
     ſeyn
    0.76
    <unused76>
    0.76
    <unused41>
    0.76
    <unused20>
    0.76
    <unused74>
    0.75
     ſelb
    0.75
    <unused42>
    0.75
    <pad>
    0.75
    Act Density 1.102%

    No Known Activations