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

    Neuronpedia

    INDEX
    Explanations

    structured data and formatting elements typically used in technical documents or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.03
     FetchType
    -1.03
     Efq
    -1.02
     ſever
    -1.01
     pleaſure
    -0.97
     ſtate
    -0.95
     reaſon
    -0.95
     Reſ
    -0.94
     ſta
    -0.92
     Diſ
    -0.92
    POSITIVE LOGITS
     
    0.48
     en
    0.46
     so
    0.45
     The
    0.42
    ysz
    0.37
     men
    0.37
     h
    0.37
     kont
    0.37
    Vendo
    0.37
     arus
    0.36
    Act Density 0.453%

    No Known Activations