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

    Neuronpedia

    INDEX
    Explanations

    phrases related to qualities and descriptions of objects or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.56
     fullName
    -0.56
     $_(
    -0.54
     getattr
    -0.53
     fry
    -0.50
     honorary
    -0.49
     PyTuple
    -0.48
     borderRadius
    -0.48
     Honorary
    -0.47
     maxn
    -0.47
    POSITIVE LOGITS
     때문
    0.40
    łaszcza
    0.40
     accesibles
    0.40
     suaminya
    0.39
     temprana
    0.38
    postsleuth
    0.37
    Personensuche
    0.37
     navideña
    0.37
    ไง
    0.36
     absence
    0.36
    Act Density 0.612%

    No Known Activations