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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing clear and specific information

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases indicating clarity and decisiveness in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uel
    -0.59
    Stand
    -0.57
     stub
    -0.54
     haze
    -0.53
    ulhu
    -0.53
     mun
    -0.53
    IRE
    -0.53
     Expert
    -0.52
    ets
    -0.52
    hern
    -0.52
    POSITIVE LOGITS
     about
    1.22
     enough
    1.13
    about
    1.13
     ABOUT
    1.07
    enough
    0.98
     regarding
    0.94
     About
    0.93
    footed
    0.84
    ially
    0.82
     Regarding
    0.80
    Act Density 0.169%

    No Known Activations