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

    Neuronpedia

    INDEX
    Explanations

    nouns related to physical objects or actions

    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
    etsk
    -0.95
    iments
    -0.82
    ATURES
    -0.81
    angles
    -0.76
    arten
    -0.74
     outputs
    -0.74
    reports
    -0.73
    orders
    -0.73
     encour
    -0.73
    ographs
    -0.72
    POSITIVE LOGITS
     bunch
    0.89
     nutshell
    0.88
     single
    0.87
     multitude
    0.82
     woman
    0.82
     couple
    0.82
     small
    0.82
     particular
    0.82
     dozen
    0.81
     defunct
    0.80
    Act Density 0.166%

    No Known Activations