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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various aspects or features of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rena
    -0.63
    Carriera
    -0.61
    katan
    -0.56
     Mazar
    -0.56
     Zyg
    -0.54
     Borel
    -0.53
    spath
    -0.53
     nephe
    -0.53
     Lightboxes
    -0.53
    exper
    -0.53
    POSITIVE LOGITS
     AssemblyTitle
    0.85
     aspect
    0.84
    aspect
    0.71
     vez
    0.70
    aspetto
    0.69
    AndroidJUnit
    0.69
     Aspect
    0.65
     ilg
    0.65
    makedirs
    0.62
    сюда
    0.62
    Act Density 0.075%

    No Known Activations