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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completion or achievement

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siber
    -0.57
     demos
    -0.56
     itiner
    -0.56
     pots
    -0.56
     Pharaoh
    -0.56
     masses
    -0.54
     pract
    -0.54
    apixel
    -0.54
     Rebell
    -0.53
     coff
    -0.53
    POSITIVE LOGITS
    nown
    0.92
    ources
    0.84
    ̶
    0.83
    ustainable
    0.82
    por
    0.81
    adi
    0.79
    lightly
    0.79
    âĹ
    0.78
    oda
    0.76
    -->
    0.75
    Act Density 0.080%

    No Known Activations