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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to scientific discoveries and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     para
    -0.29
     mes
    -0.27
     h
    -0.27
     pro
    -0.27
     apple
    -0.26
     au
    -0.25
     er
    -0.25
    : 
    -0.24
     then
    -0.24
    urlencoded
    -0.24
    POSITIVE LOGITS
     tartalomajánló
    0.73
     queſta
    0.71
    majánló
    0.70
    <unused8>
    0.70
    tagHelperRunner
    0.69
    <unused52>
    0.69
    <unused79>
    0.69
    <unused47>
    0.69
    <pad>
    0.69
    <unused23>
    0.69
    Act Density 0.217%

    No Known Activations