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

    Neuronpedia

    INDEX
    Explanations

    terms related to processes and techniques in technical or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.76
     ProtoMessage
    -0.61
    Personendaten
    -0.60
    Diweddarwch
    -0.58
    WillAppear
    -0.56
    варь
    -0.55
     noastre
    -0.54
    
    -0.52
    ناك
    -0.52
    Aiheesta
    -0.52
    POSITIVE LOGITS
    ImageContext
    0.66
    |/
    0.64
    antMatchers
    0.61
     CRITICAL
    0.60
    platin
    0.60
    FORMANCE
    0.60
    ENEFITS
    0.60
    PDIR
    0.59
    RefNanny
    0.59
    volving
    0.59
    Act Density 0.756%

    No Known Activations