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

    Neuronpedia

    INDEX
    Explanations

    skills related to interpersonal relationships or personal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.69
    ⓧ
    -0.69
     Италијани
    -0.67
    featureID
    -0.66
    parsedMessage
    -0.63
    principalTable
    -0.60
    Czytaj
    -0.60
    ніципалі
    -0.59
    bech
    -0.58
     solche
    -0.58
    POSITIVE LOGITS
     “
    0.52
    ↵
    0.51
      
    0.48
     trend
    0.48
     re
    0.44
     progress
    0.44
     Chief
    0.44
     d
    0.40
     de
    0.39
     
    0.39
    Act Density 0.320%

    No Known Activations