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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or discuss a topic

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'light' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irlf
    -0.79
    apego
    -0.79
     Legisl
    -0.77
     Merrill
    -0.77
    remlin
    -0.74
     Forever
    -0.72
    ihu
    -0.70
     Carnegie
    -0.67
    UGE
    -0.67
    irie
    -0.66
    POSITIVE LOGITS
    enment
    1.12
    ening
    1.02
    weights
    0.94
    ened
    0.92
    ener
    0.87
     bulb
    0.86
    eners
    0.86
    nings
    0.80
    heartedly
    0.79
    hearted
    0.79
    Act Density 0.016%

    No Known Activations