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

    Neuronpedia

    INDEX
    Explanations

    conjunctions linking related ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used to connect thoughts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dunk
    -0.64
    éĹĺ
    -0.62
    jury
    -0.61
     Jav
    -0.60
    ilty
    -0.56
    CRIP
    -0.55
    ainted
    -0.55
    ://
    -0.55
     Stein
    -0.53
     HIP
    -0.52
    POSITIVE LOGITS
    rogen
    1.46
    rogens
    1.36
    ro
    0.92
    romeda
    0.90
    rew
    0.88
    then
    0.87
    rost
    0.83
    RO
    0.82
    rology
    0.79
    rea
    0.79
    Act Density 0.128%

    No Known Activations