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

    Neuronpedia

    INDEX
    Explanations

    mention of body parts or attributes related to the back area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desmotivaciones
    -1.23
     queſta
    -1.23
     ainfi
    -1.19
    <unused74>
    -1.15
    <unused51>
    -1.15
    <unused16>
    -1.15
    <unused14>
    -1.14
    <unused23>
    -1.14
    <unused8>
    -1.14
    <unused3>
    -1.14
    POSITIVE LOGITS
    ↵
    0.65
     (
    0.60
    ,
    0.59
     front
    0.58
     
    0.56
    “
    0.56
     live
    0.53
      
    0.51
    -
    0.51
     DIY
    0.50
    Act Density 0.839%

    No Known Activations