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

    Neuronpedia

    INDEX
    Explanations

    references to people's backgrounds or associations

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    easy
    -0.76
    evidence
    -0.74
    agree
    -0.71
    encies
    -0.70
     IMAGES
    -0.70
     Actions
    -0.69
     alerts
    -0.69
     docs
    -0.67
    views
    -0.67
    iev
    -0.67
    POSITIVE LOGITS
     handful
    0.93
     dozen
    0.88
     whopping
    0.87
     mixture
    0.83
    unts
    0.83
     lot
    0.82
     sizeable
    0.82
     similar
    0.81
     sizable
    0.80
    lyss
    0.80
    Act Density 0.574%

    No Known Activations