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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the impact or importance of different entities or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fork
    -0.70
    Joined
    -0.68
    Allows
    -0.68
    pin
    -0.67
    buster
    -0.67
    Hub
    -0.66
     besides
    -0.65
    FILE
    -0.65
    âĢł
    -0.65
    anooga
    -0.65
    POSITIVE LOGITS
     aforementioned
    1.19
     entirety
    1.14
     rest
    1.13
     slightest
    1.10
     remainder
    1.08
     latter
    1.07
     smallest
    1.03
     broader
    1.00
     occasional
    1.00
     possibility
    0.99
    Act Density 0.663%

    No Known Activations