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

    Neuronpedia

    INDEX
    Explanations

    phrases surrounded by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.79
    stant
    -0.76
    ¿
    -0.75
    ¾
    -0.75
    ãĤ¨ãĥ«
    -0.66
    ¸
    -0.66
    ĻĤ
    -0.65
    ailing
    -0.65
    ctuary
    -0.65
    ãĥ¥
    -0.65
    POSITIVE LOGITS
    /"
    1.17
     moniker
    0.86
     aka
    0.83
     mentality
    0.74
     whereby
    0.70
     designation
    0.70
    aneers
    0.70
     wherein
    0.69
     ("
    0.68
     mantra
    0.68
    Act Density 0.078%

    No Known Activations