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

    Neuronpedia

    INDEX
    Explanations

    instructions and recommendations about practical tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.60
    incredible
    -0.57
     unprecedented
    -0.57
    ďaka
    -0.56
     malheureusement
    -0.50
     navnet
    -0.50
    なんと
    -0.50
     necesite
    -0.49
    TypeDefinition
    -0.49
     noDo
    -0.49
    POSITIVE LOGITS
     preferably
    1.38
    preferably
    1.30
     Preferably
    1.07
     suitable
    0.96
     reputable
    0.96
     atleast
    0.95
     appropriate
    0.90
     préférence
    0.89
     möglichst
    0.87
     reliable
    0.86
    Act Density 0.400%

    No Known Activations