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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprom
    -0.72
     downgrade
    -0.72
     grid
    -0.70
     technical
    -0.70
     industrial
    -0.66
     CONTROL
    -0.66
     laun
    -0.66
     SYSTEM
    -0.65
     Masquerade
    -0.65
     CMS
    -0.64
    POSITIVE LOGITS
    elia
    1.11
    annah
    1.08
    rice
    1.07
    zzy
    1.04
    atalie
    1.02
    othy
    1.01
    iane
    1.00
    Jenn
    1.00
    andra
    1.00
    ricia
    0.99
    Act Density 0.175%

    No Known Activations