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

    Neuronpedia

    INDEX
    Explanations

    instances where actions are being taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.69
    times
    -0.66
    Autom
    -0.65
    Attach
    -0.65
     attributes
    -0.65
     greets
    -0.64
    CI
    -0.63
     eyed
    -0.63
    tions
    -0.62
    peed
    -0.62
    POSITIVE LOGITS
     mistake
    0.92
     contribution
    0.88
     fuss
    0.88
     difference
    0.85
     distinction
    0.85
     comeback
    0.85
     lot
    0.84
     habit
    0.83
     cameo
    0.81
     pact
    0.81
    Act Density 0.079%

    No Known Activations