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

    Neuronpedia

    INDEX
    Explanations

    words related to software development and updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     diplom
    -0.73
    etheless
    -0.72
    lessly
    -0.67
     CPC
    -0.65
     treating
    -0.64
     hoops
    -0.64
     wholesale
    -0.63
     admitting
    -0.63
     AFL
    -0.62
     scales
    -0.61
    POSITIVE LOGITS
    eker
    1.27
    vere
    1.24
    ldom
    1.21
    gments
    1.19
    infeld
    1.13
    xton
    1.09
    greg
    1.08
    vered
    1.08
    eps
    1.08
    gment
    1.07
    Act Density 0.017%

    No Known Activations