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

    Neuronpedia

    INDEX
    Explanations

    phrases describing a feature or capability that can be 'used' for various purposes in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various forms and contexts, indicating the state of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obscurity
    -0.75
     Matters
    -0.71
    gling
    -0.66
     Guilty
    -0.65
    erity
    -0.65
     Rab
    -0.64
     Notting
    -0.62
     Dare
    -0.62
     impossibility
    -0.62
     Blaz
    -0.62
    POSITIVE LOGITS
     accessed
    1.15
     reused
    1.13
     used
    1.10
     exchanged
    1.09
     swapped
    1.08
     purchased
    1.06
     manually
    1.05
     optionally
    1.05
     inspected
    1.04
     utilized
    1.04
    Act Density 0.116%

    No Known Activations