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

    Neuronpedia

    INDEX
    Explanations

    formal scientific language and expressions related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.77
     Efq
    -0.72
    PyExc
    -0.70
     pleaſure
    -0.67
     lenker
    -0.65
    Cyfeiriadau
    -0.64
     habet
    -0.64
     '\\;'
    -0.64
     Theſe
    -0.59
    Enllaces
    -0.59
    POSITIVE LOGITS
     researchers
    0.70
     authors
    0.67
    authors
    0.64
     research
    0.63
    ABSTRACT
    0.62
    Researchers
    0.60
     study
    0.60
     Researchers
    0.58
     연구
    0.58
    发表于
    0.56
    Act Density 2.969%

    No Known Activations