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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating essential or fundamental aspects

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "basically" is used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nor
    -0.65
    tis
    -0.65
     Others
    -0.64
    eth
    -0.64
     Visitors
    -0.61
    aud
    -0.61
    ©
    -0.60
    ®
    -0.60
     Yet
    -0.57
    "},{"
    -0.57
    POSITIVE LOGITS
     basically
    3.11
     essentially
    2.23
    Basically
    1.99
     Basically
    1.94
     kinda
    1.72
     literally
    1.65
     practically
    1.47
     pretty
    1.45
     obviously
    1.37
     Essentially
    1.34
    Act Density 0.022%

    No Known Activations