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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to scientific inventions and processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
      
    -0.45
     b
    -0.45
     [
    -0.40
    +
    -0.40
     z
    -0.40
    ({
    -0.39
    [
    -0.39
    ich
    -0.38
    ensio
    -0.37
    –
    -0.37
    POSITIVE LOGITS
     Monfieur
    1.19
     Efq
    1.12
    findpost
    1.04
     myſelf
    1.03
     itſelf
    1.02
     betweenstory
    1.01
     auffi
    1.00
    contentLoaded
    0.98
    ſelves
    0.98
    InjectAttribute
    0.96
    Act Density 0.341%

    No Known Activations