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

    Neuronpedia

    INDEX
    Explanations

    words related to statistics and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stuff
    -0.70
    someone
    -0.69
    =$
    -0.68
    deen
    -0.67
    eva
    -0.67
    orate
    -0.65
     Someone
    -0.64
    alion
    -0.64
     Sutherland
    -0.64
     Isn
    -0.61
    POSITIVE LOGITS
     staffed
    1.05
     acad
    1.00
     hybrids
    1.00
     havens
    0.99
     clustered
    0.99
     designed
    0.94
     democracies
    0.94
     riddled
    0.94
     hubs
    0.93
     plagued
    0.93
    Act Density 0.247%

    No Known Activations