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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions, particularly Oxford University

    oai_token-act-pair · gpt-3.5-turbo

    references to the University of Oxford and related institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ++++++++++++++++
    -0.81
    ACTED
    -0.73
    ////////
    -0.72
    RANT
    -0.72
    Magikarp
    -0.71
    selage
    -0.69
    ++++++++
    -0.69
    SHIP
    -0.69
    VICE
    -0.68
    ////////////////
    -0.67
    POSITIVE LOGITS
    shire
    1.51
    bridge
    0.94
     Circus
    0.93
     comma
    0.86
    hurst
    0.85
     Oxford
    0.84
     Manor
    0.78
    ington
    0.77
    nard
    0.76
    gate
    0.76
    Act Density 0.018%

    No Known Activations