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

    Neuronpedia

    INDEX
    Explanations

    descriptions of various views or vistas

    oai_token-act-pair · gpt-3.5-turbo

    references to scenic views

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.88
    vous
    -0.76
     notor
    -0.70
    zzy
    -0.69
     tightening
    -0.67
    ursed
    -0.67
    pmwiki
    -0.67
     surn
    -0.65
    ciating
    -0.65
    encies
    -0.64
    POSITIVE LOGITS
    finder
    1.13
    ports
    1.09
    port
    1.04
    ById
    0.95
    screen
    0.82
    model
    0.80
    points
    0.79
    enery
    0.79
    tower
    0.77
    ults
    0.76
    Act Density 0.028%

    No Known Activations