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

    Neuronpedia

    INDEX
    Explanations

    references to specific cases or instances that suggest a situation or argument

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.72
    Captor
    -0.69
     AssemblyCompany
    -0.69
    Autoritní
    -0.68
     houſe
    -0.66
     myſelf
    -0.65
     Exactos
    -0.63
     doInBackground
    -0.62
     himſelf
    -0.59
     Reſ
    -0.58
    POSITIVE LOGITS
     Då
    0.65
     wtedy
    0.63
     dann
    0.60
    Då
    0.60
     réduite
    0.58
     då
    0.57
     Then
    0.56
     entonces
    0.56
    Allora
    0.54
     then
    0.52
    Act Density 0.511%

    No Known Activations