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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events performed by someone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grounds
    -0.73
    evidence
    -0.71
    Iss
    -0.71
    estate
    -0.70
    atcher
    -0.70
    ombat
    -0.68
    adj
    -0.68
    encies
    -0.67
     Industries
    -0.65
    onto
    -0.64
    POSITIVE LOGITS
     bunch
    1.03
     handful
    0.96
     multitude
    0.92
     plethora
    0.92
     few
    0.90
     variety
    0.90
     lot
    0.88
     huge
    0.85
     slight
    0.85
     mixture
    0.85
    Act Density 0.197%

    No Known Activations