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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.72
    protoc
    -0.70
     privatisation
    -0.61
    styleable
    -0.59
     stabilisation
    -0.58
    +#+
    -0.57
     shewn
    -0.57
    исленность
    -0.56
    ")));
    -0.56
     modernisation
    -0.55
    POSITIVE LOGITS
     then
    0.69
     put
    0.66
    AnchorStyles
    0.61
    ligently
    0.59
     start
    0.56
    ViewFeatures
    0.55
    then
    0.55
    mentet
    0.55
     незавершена
    0.54
    Zeneca
    0.54
    Act Density 0.304%

    No Known Activations