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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sit"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iler
    -0.79
    raid
    -0.75
    effective
    -0.71
    enforcement
    -0.69
    ilers
    -0.68
    EStreamFrame
    -0.67
    anticipated
    -0.67
    iction
    -0.65
    ASC
    -0.63
    irus
    -0.63
    POSITIVE LOGITS
     seiz
    0.87
    aution
    0.81
    lie
    0.80
     desks
    0.78
     sit
    0.78
    âĸ¬
    0.78
    âĸ¬âĸ¬
    0.77
    ivas
    0.75
    entary
    0.75
     idle
    0.74
    Act Density 0.016%

    No Known Activations