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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the passing or beginning of something, such as laws, construction projects, or historical events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" that indicate a location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ens
    -0.69
    username
    -0.66
     %%
    -0.66
    =""
    -0.65
     lodged
    -0.65
    worthy
    -0.62
    sworth
    -0.61
    casters
    -0.60
    hur
    -0.58
     learners
    -0.58
    POSITIVE LOGITS
     accordance
    1.31
     conjunction
    1.25
     vain
    1.22
     lieu
    1.22
     vitro
    1.19
    ordinate
    1.16
     unison
    1.14
     tandem
    1.10
     order
    1.08
     favor
    1.08
    Act Density 0.568%

    No Known Activations