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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cleanliness and tidiness

    oai_token-act-pair · gpt-3.5-turbo

    commas in context of sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.71
    ½
    -0.69
    rio
    -0.66
    è£ħ
    -0.65
    UF
    -0.63
    izen
    -0.62
    ¥
    -0.62
    ãĤ¨ãĥ«
    -0.62
    ISION
    -0.61
    rament
    -0.61
    POSITIVE LOGITS
     however
    1.11
     though
    1.09
     whereas
    1.07
     although
    1.01
     but
    1.00
     which
    0.88
     albeit
    0.83
     meanwhile
    0.81
     namely
    0.78
     moreover
    0.76
    Act Density 0.618%

    No Known Activations