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

    Neuronpedia

    INDEX
    Explanations

    phrases related to regular or frequent occurrences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "regularly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geh
    -0.76
    lad
    -0.69
    elo
    -0.68
     Mara
    -0.65
     Millennium
    -0.65
    soc
    -0.64
    shi
    -0.63
    holes
    -0.62
     Warriors
    -0.62
     Shape
    -0.62
    POSITIVE LOGITS
    theless
    0.99
     spaced
    0.94
    entimes
    0.90
     encountered
    0.89
     Asked
    0.87
     consulted
    0.85
     encount
    0.83
     employed
    0.82
     monitored
    0.82
     complained
    0.78
    Act Density 0.029%

    No Known Activations