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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to instability or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    adjectives related to texture or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supplemented
    -0.67
     conveyed
    -0.65
    ership
    -0.63
     Kinnikuman
    -0.62
     Prol
    -0.62
    inators
    -0.62
    ials
    -0.62
    âĢ¢âĢ¢
    -0.61
    ified
    -0.60
    ogue
    -0.59
    POSITIVE LOGITS
    aky
    1.33
    zzy
    1.02
    tty
    0.99
    arak
    0.95
    nesses
    0.92
    uga
    0.87
    ny
    0.85
    clean
    0.83
    akin
    0.83
    asy
    0.83
    Act Density 0.011%

    No Known Activations