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

    Neuronpedia

    INDEX
    Explanations

    details related to updates and changes in various situations or news events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    AE
    -0.67
    âĹ¼
    -0.66
    mberg
    -0.63
     Unlock
    -0.60
    SU
    -0.59
    Draft
    -0.58
    Move
    -0.58
    jriwal
    -0.58
     Reconstruction
    -0.57
    DD
    -0.56
    POSITIVE LOGITS
    ened
    1.01
     than
    0.97
    ening
    0.95
    ons
    0.94
     fortunate
    0.85
    ens
    0.77
    ington
    0.76
    nesses
    0.75
    than
    0.74
    ener
    0.74
    Act Density 0.032%

    No Known Activations