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

    Neuronpedia

    INDEX
    Explanations

    keywords related to approvals, especially with the word "approach"

    oai_token-act-pair · gpt-3.5-turbo

    words related to approaches and arrivals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.71
    avorite
    -0.68
     Opera
    -0.66
     Georgian
    -0.65
     Leilan
    -0.63
    ATA
    -0.62
     Thirty
    -0.62
     Danish
    -0.62
     HMS
    -0.61
     Insider
    -0.61
    POSITIVE LOGITS
    ving
    1.38
    ves
    1.19
    ven
    1.19
    ved
    1.19
    pped
    1.18
    ctions
    1.18
    ple
    1.14
    ller
    1.12
    pping
    1.11
    pper
    1.10
    Act Density 0.044%

    No Known Activations