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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different versions or editions of a particular entity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    urers
    -0.84
    phasis
    -0.81
    arers
    -0.76
    ateurs
    -0.74
    oji
    -0.70
    ussion
    -0.67
    roma
    -0.67
    hya
    -0.66
    ering
    -0.66
    earchers
    -0.65
    POSITIVE LOGITS
     Fortune
    0.67
     Flip
    0.65
     fortune
    0.63
     Thing
    0.63
     sorts
    0.63
     PowerPoint
    0.63
     Adventures
    0.62
     events
    0.62
     theirs
    0.62
     Windows
    0.60
    Act Density 0.086%

    No Known Activations