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

    Neuronpedia

    INDEX
    Explanations

    verbs related to aggressive physical actions

    oai_token-act-pair · gpt-3.5-turbo

    labels or descriptors related to consumption or physical actions involving objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CRIP
    -0.78
    alam
    -0.70
    oft
    -0.69
    ashtra
    -0.67
    WP
    -0.64
    Initialized
    -0.63
    omething
    -0.61
    arium
    -0.60
    naire
    -0.60
     Edison
    -0.60
    POSITIVE LOGITS
    bing
    2.23
    bed
    1.88
    bling
    1.87
    bled
    1.82
    bles
    1.74
    ber
    1.70
    bers
    1.70
    blers
    1.66
    bler
    1.63
    ble
    1.61
    Act Density 0.129%

    No Known Activations